git commit finalize app

Signed-off-by: Yotam Perlitz <[email protected]>

.gitignore

@@ -0,0 +1,3 @@
+.vscode/launch.json
+.vscode/settings.json
+.DS_Store

app.py

@@ -1,117 +1,413 @@
-import streamlit as st
+import hashlib
+import os
+
 import pandas as pd
+import plotly.express as px
+import streamlit as st
+from bat import Benchmark, Config, Reporter, Tester
+from bat.utils import get_holistic_benchmark
+
+benchmarks_dict = {
+    "arena_elo": "LMSys Arena",
+    "mt_bench": "MT Bench",
+    "mixeval": "Mix Eval",
+    "alpacav2": "AlpacaEval V2",
+    "arena_hard": "Arena Hard",
+    "arc_c": "ARC-C",
+    "eq_benchv2": "EQ Bench V2",
+    "agieval": "AGIEval",
+    "llmonitor": "LLMonitor",
+    "bbh": "BBH",
+    "mmlu": "MMLU",
+    "alpacav1": "AlpacaEval V1",
+    "magi": "MAGI",
+    "alpacaeval2_lc": "AlpacaEval V2 Length Adjusted",
+    "gpt4all": "GPT-4-All",
+    "humaneval": "HumanEval",
+    "mbpp": "MBPP",
+    "hellaswag": "HellaSwag",
+    "hugging_6": "HF OpenLLM V1",
+    "winogrande": "Winogrande",
+}
+
+st.markdown(
+    """<h1 style='text-align: center; color: black;'>🏋️‍♂️ BenchBench Leaderboard 🏋️‍♂️</h1>""",
+    unsafe_allow_html=True,
+)
+
+st.markdown(
+    "We are excited to share the BenchBench-Leaderboard, a crucial component of our comprehensive research on Benchmark Agreement Testing (BAT) [work](#). "
+    "This leaderboard is a meta-benchmark that ranks benchmarks based on their agreement with the crowd harnessing many different references. "
+)
+
+
+all_scenarios_for_aggragate = get_holistic_benchmark().get_scenarios()
+
+st.subheader("The Leaderboard", divider=True)
+# st.subheader("🏋️‍♂️ BenchBench Leaderboard 🏋", divider=True)
+
+leftcol, rightcol = st.columns([2, 1])
+with leftcol:
+    with st.expander("Leaderboard configurations (defaults are great BTW)", icon="⚙️"):
+        with st.form("my_form"):
+            all_scenarios_for_aggragate_with_all = all_scenarios_for_aggragate.tolist()
+            all_scenarios_for_aggragate_with_all.append("All Holistic")
+
+            aggragate_scenarios = st.multiselect(
+                "Scenarios in Aggregate",
+                all_scenarios_for_aggragate_with_all,
+                ["All Holistic"],
+                # all_scenarios_for_aggragate,
+            )
+
+            corr_type = st.selectbox(
+                label="Select Correlation type", options=["kendall", "pearson"], index=0
+            )
+
+            aggragate_scenario_blacklist = (
+                [
+                    scen
+                    for scen in all_scenarios_for_aggragate
+                    if scen not in aggragate_scenarios
+                ]
+                if "All Holistic" not in aggragate_scenarios
+                else []
+            )
+
+            model_select_strategy = st.selectbox(
+                label="Select strategy",
+                options=["random", "top_aggregate", "somewhere_aggregate"],
+                index=0,
+            )
+
+            n_models_taken_list = [5]
+            n_exps = 10
+
+            submitted = st.form_submit_button(label="Run BAT")
+
+with rightcol:
+    st.button("➕ Add your benchmark here!")
+
+
+def run_load(
+    aggragate_scenario_blacklist=[],
+    n_models_taken_list=[5],
+    model_select_strategy_list=["random"],
+    corr_types=["kendall"],
+    n_exps=10,
+):
+    # Create a hash of the inputs to generate a unique cache file for each set of inputs
+    input_str = (
+        str(aggragate_scenario_blacklist)
+        + str(n_models_taken_list)
+        + str(model_select_strategy_list)
+        + str(corr_types)
+        + str(n_exps)
+    )
+    input_hash = hashlib.md5(input_str.encode()).hexdigest()
+    cache_file = f"agreements_cache_{input_hash}.csv"
+
+    # Define the cache directory
+    cache_dir = "cache"
+    cache_path = os.path.join(cache_dir, cache_file)
+
+    # Check if the cache file exists
+    if os.path.exists(cache_path):
+        print("Loading cached results...")
+        agreements = pd.read_csv(cache_path)
+        return agreements
+
+    else:
+        print("Cached results not found, calculating")
+
+        cfg = Config(
+            exp_to_run="example",
+            n_models_taken_list=n_models_taken_list,
+            model_select_strategy_list=model_select_strategy_list,
+            corr_types=corr_types,
+            n_exps=n_exps if n_models_taken_list != [0] else 1,
+            # reference_data_path="data/combined_holistic.csv",
+        )
+
+        holistic = get_holistic_benchmark()
+        holistic_scenarios = holistic.get_scenarios()
+        holistic.clear_repeated_scenarios()
+        holistic.add_aggragete(
+            new_col_name="aggregate",
+            agg_source_name="holistic",
+            scenario_blacklist=aggragate_scenario_blacklist,
+            min_scenario_for_models_to_appear_in_agg=5,
+        )
+
+        allbench = Benchmark(
+            pd.read_csv("assets/combined_20240704.csv"),
+            # data_source=newbench_name,
+        )
+        allbench.df = allbench.df.drop(columns=["tag"])
+        allbench.clear_repeated_scenarios()
+        allbench.df = allbench.df.query("scenario not in @holistic_scenarios")
+
+        allbench.df = allbench.df[~allbench.df["scenario"].str.contains("_mixed")]
+        allbench.df = allbench.df[~allbench.df["scenario"].str.contains("agentbench")]
+
+        # st.dataframe(holistic.df.query('scenario=="aggregate"'))
+
+        allbench = allbench.extend(holistic)
+
+        tester = Tester(cfg=cfg)
+
+        # len(allbench.get_scenario_appearences_count().keys())
+
+        agreements = tester.all_vs_all_agreement_testing(
+            allbench, single_source_scenario="aggregate"
+        )
+
+        agreements.to_csv(cache_path, index=False)
+
+    return agreements
+
+
+agreements = run_load(
+    aggragate_scenario_blacklist=aggragate_scenario_blacklist,
+    n_models_taken_list=n_models_taken_list,
+    model_select_strategy_list=[model_select_strategy],
+    corr_types=[corr_type],
+    n_exps=n_exps,
+)
+
+reporter = Reporter()
+z_scores = reporter.get_all_z_scores(agreements=agreements, aggragate_name="aggregate")
+
+corr_name = f"{'KT' if corr_type=='kendall' else 'Per.'} Corr."
+
+z_scores["z_score"] = z_scores["z_score"].round(2)
+z_scores["corr_with_agg"] = z_scores["corr_with_agg"].round(2)
+z_scores["p_value_of_corr_with_agg"] = z_scores["p_value_of_corr_with_agg"].round(2)
+
+data = (
+    z_scores.rename(
+        columns={
+            "scenario": "Benchmark",
+            "z_score": "Z Score",
+            "corr_with_agg": corr_name,
+            "p_value_of_corr_with_agg": "p value of Corr.",
+            "source": "Source",
+        }
+    )
+    .sort_values("Z Score", ascending=False)
+    .reset_index(drop=True)
+)
+
+
+data = data[~data["Source"].str.contains("livebench")]
+data = data[~data["Source"].str.contains("biggen")]
+data.drop(columns=["Source"], inplace=True)
+data["Benchmark"] = data["Benchmark"].apply(lambda x: benchmarks_dict[x])
+
+# Apply coloring based on 'Z' valuesz
+
+styled_data = data.style.background_gradient(
+    subset=["Z Score"],
+    cmap="RdYlGn",
+    vmin=-data["Z Score"].abs().max(),
+    vmax=data["Z Score"].abs().max(),
+).format(subset=["Z Score", corr_name, "p value of Corr."], formatter="{:.2}")
+
+st.dataframe(
+    data=styled_data,
+    hide_index=True,
+    use_container_width=True,
+    height=300,
+)
+
+st.markdown(
+    "BenchBench-Leaderboard complements our study, where we analyzed over 40 prominent benchmarks and introduced standardized practices to enhance the robustness and validity of benchmark evaluations through the [BenchBench Python package](#). "
+    "The BenchBench-Leaderboard serves as a dynamic platform for benchmark comparison and is an essential tool for researchers and practitioners in the language model field aiming to select and utilize benchmarks effectively. "
+)
+
+st.subheader("How did we get the Z Scores?", divider=True)
+
+st.write(r"""
+            Section 3.1 in our work shows how using a single reference benchmark drastically hurts the roubustness and validity of BAT.
+            To remedy this, we propose to test benchmark agreement with an aggragate benchmark and compare the agreement to other benchmarks.
+            We recommend to perform this comparison using the [Z score](https://en.wikipedia.org/wiki/Standard_score) and demonstrate obtaining it to a benchmark of your selection.
+            In the follwing way: $z_i=(x_i-\mu_{i...N}) / \sigma_{i...N}$ where $x_i$ is the agreement of the $i$th benchmark to the aggragate and $\mu_{i...N}$,$\sigma_{i...N}$ are the 
+            mean and standard deviation of the agreements of the other benchmarks to the aggragate.
+            """)
+
+
+benchmarks = data["Benchmark"].unique().tolist()
+plotted_scenario = st.selectbox(
+    "Choose Benchmark to plot", benchmarks, index=benchmarks.index("LMSys Arena")
+)
+
+
+fig = px.histogram(
+    data.query("Benchmark!=@plotted_scenario"), x=corr_name, nbins=len(data) - 1
+)
+# Add a vertical line at a specific x-coordinate
+# Replace 'x_value' with the actual value where you want the line
+x_value = 0.5  # Example value, adjust as necessary
+fig.add_vline(
+    x=data.query("Benchmark==@plotted_scenario")[corr_name].iloc[0],
+    line_dash="dash",
+    line_color="red",
+)
+# Update layout to add a title
+fig.update_layout(
+    title="Histogram of Correlation Values",  # Change the title text as needed
+    title_x=0.3,  # Centers the title
+    title_font=dict(size=20, family="CMU"),  # Customize font if needed
+)
+
+# # Plot!
+st.plotly_chart(fig, use_container_width=True)
+
+st.subheader("Why should you use the BenchBench Leaderboard?")
+
+st.markdown(
+    """
+
+    Current practices in Benchmark Agreement Testing (BAT) often suffer from a lack of standardization and transparency, which can lead to inconsistent results and diminished trust in benchmark evaluations. Several key issues are prevalent in the field:
+
+    """
+)
+
+st.markdown(
+    """
+    - **Lack of Standard Methodologies:** Unlike other scientific procedures that follow rigorous methodologies, BAT lacks uniform procedures across different studies. Researchers often employ varied criteria for selecting benchmarks and models for comparison, which leads to results that cannot be easily compared or replicated. This variation undermines the reliability of conclusions drawn from BAT and makes it difficult for other researchers to build on existing work.
+    """
+)
+
+st.image(
+    "assets/motivation.png",
+    caption="Conclusions depend on the models considered. Kendall-tau correlations between the LMSys Arena benchmark and three other benchmarks: BBH, MMLU, and Alpaca v2. Each group of bars represents the correlation for different sets of top models, specifically the top 5, top 10, and top 15 (overlapping) models (according to the Arena). The results indicate that the degree of agreement between benchmarks varies with the number of top models considered, highlighting that different selections of models can lead to varying conclusions about benchmark agreement.",
+    use_column_width=True,
+)
+
+st.markdown(
+    """
+    - **Arbitrary Selection of Reference Benchmarks:** One of the most critical decisions in BAT is the choice of reference benchmarks. Currently, this choice is often arbitrary and lacks a clear rationale, influenced by availability or personal preference rather than strategic alignment with the benchmark’s purpose. This can skew the results significantly, as different benchmarks may not be equally representative or relevant to the models being tested.
+    """
+)
+st.markdown(
+    """
+    - **Inadequate Model Representation:** BAT frequently relies on a limited subset of models, which may not comprehensively represent the diversity of architectures and training paradigms in modern language models. This selective representation can lead to biased agreement scores that favor certain types of models over others, failing to provide a holistic view of model performance across different benchmarks.
+    """
+)
 
-st.title("‎‎‎  ‎‎ ‎ ‎ ‎ ‎ ‎ ‎🏋️‍♂️ benchbench-Leaderboard 🏋️‍♂️")
+st.image(
+    "assets/pointplot_granularity_matters.png",
+    caption="Correlations increase with number of models. Mean correlation (y) between each benchmark (lines) and the rest, given different numbers of models. The Blue and Orange lines are the average of all benchmark pair correlations with models sampled randomly (orange) or in contiguous sets (blue). The shaded lines represents adjacent sampling for the different benchmarks.",
+    use_column_width=True,
+)
+
+st.markdown(
+    """
+    - **Overemphasis on Correlation Metrics:** Current BAT practices tend to over-rely on correlation metrics without adequately considering their limitations and the context of their application. While these metrics can provide useful insights, they are often treated as definitive evidence of agreement without acknowledging that high correlation does not necessarily imply conceptual alignment between benchmarks.
+    """
+)
+
+st.markdown(
+    """
+    To address these issues, there is a critical need for a more structured approach to BAT that includes clear guidelines for benchmark and model selection, a broader consideration of agreement metrics, and an acknowledgment of the evolving nature of technology in this space. By reforming BAT practices, the research community can improve the reliability and utility of benchmarks as tools for evaluating and advancing language models.
+    """
+)
+
+
+st.image(
+    "assets/ablations.png",
+    caption="Our recommendations substantially reduce the variance of BAT. Ablation analysis for each BAT recommendation separately and their combinations.",
+    use_column_width=True,
+)
+
+
+st.header("The BenchBench package")
+
+st.markdown("""
+### Overview
+
+The BAT package is designed to facilitate benchmark agreement testing for NLP models. It allows users to easily compare multiple models against various benchmarks and generate comprehensive reports on their agreement.
+
+### Installation
 
+To install the BAT package, you can use pip:
+
+```
+pip install bat-package
+```
+
+### Usage Example
+
+Below is a step-by-step example of how to use the BAT package to perform agreement testing.
+
+#### Step 1: Configuration
+
+First, set up the configuration for the tests:
+
+```python
 import pandas as pd
 from bat import Tester, Config, Benchmark, Reporter
 from bat.utils import get_holistic_benchmark
 
-
 cfg = Config(
     exp_to_run="example",
     n_models_taken_list=[0],
     model_select_strategy_list=["random"],
-    n_exps=10,
-    # reference_data_path="data/combined_holistic.csv",
+    n_exps=10
 )
+```
 
+#### Step 2: Fetch Model Names
 
-newbench_name = "livebench"
-new_bench_agg_name = f"{newbench_name}_mwr"
+Fetch the names of the reference models to be used for scoring:
 
+```python
 tester = Tester(cfg=cfg)
+models_for_benchmark_scoring = tester.fetch_reference_models_names(
+    reference_benchmark=get_holistic_benchmark(), n_models=20
+)
+print(models_for_benchmark_scoring)
+```
+
+#### Step 3: Load and Prepare Benchmark
 
-# models_for_benchmark_scoring = tester.fetch_reference_models_names(
-#     reference_benchmark=get_holistic_benchmark(), n_models=20
-# )
+Load a new benchmark and add an aggregate column:
 
+```python
+newbench_name = "fakebench"
 newbench = Benchmark(
-    pd.read_csv(f"assets/{newbench_name}.csv"),
+    pd.read_csv(f"src/bat/assets/{newbench_name}.csv"),
     data_source=newbench_name,
 )
+newbench.add_aggregate(new_col_name=f"{newbench_name}_mwr")
+```
 
-# newbench.add_aggragete(new_col_name=new_bench_agg_name)
-# newbench_agreements = tester.all_vs_all_agreement_testing(newbench)
+#### Step 4: Agreement Testing
 
+Perform all-vs-all agreement testing on the new benchmark:
+
+```python
+newbench_agreements = tester.all_vs_all_agreement_testing(newbench)
 reporter = Reporter()
-# reporter.draw_agreements(
-#     newbench_agreements, ref_sources=[newbench_name], scenario_sources=[newbench_name]
-# )
+reporter.draw_agreements(newbench_agreements)
+```
+
+#### Step 5: Extend and Clean Benchmark
 
-holistic = get_holistic_benchmark()
-holistic.add_aggragete(new_col_name="aggregate", agg_source_name="holistic")
+Extend the new benchmark with holistic data and clear repeated scenarios:
 
-allbench = newbench.extend(holistic)
+```python
+allbench = newbench.extend(get_holistic_benchmark())
 allbench.clear_repeated_scenarios(source_to_keep=newbench_name)
+```
+
+#### Step 6: Comprehensive Agreement Testing
 
+Perform comprehensive agreement testing and visualize:
 
-@st.cache_data
-def run_load():
-    return tester.all_vs_all_agreement_testing(allbench)
-
-
-all_agreements = run_load()
-
-observed_scenario = "arena_elo"  # "livebench_lb"
-blacklist_sources = []  # "livebench"
-
-z_score = reporter.get_z_score(all_agreements, observed_scenario, blacklist_sources)
-
-st.write(f"zscore of {observed_scenario}: {z_score}")
-
-# df = pd.read_csv("BAT_w_arena_10_random.csv")
-# df = (
-#     (
-#         df.rename(
-#             columns={
-#                 "z_score": "Z_Score",
-#                 "benchmark": "Benchmark",
-#             }
-#         ).drop(
-#             columns=[
-#                 "Unnamed: 0",
-#                 "z_test_pass",
-#             ]
-#         )
-#     )
-#     .sort_values("Z_Score", ascending=False)
-#     .query(
-#         'Benchmark!="Aggregate" and Benchmark!="MAGI" and Benchmark!="Alpaca(v2, len adj)" and Benchmark!="GPT4All"'
-#     )
-# )
-
-
-# df.replace(
-#     {
-#         "Arena Elo": "LMSys Arena",
-#         "Hugging-6": "HF OpenLLM",
-#         "Alpaca(v2)": "Alpaca v2",
-#         "Alpaca(v1)": "Alpaca v1",
-#         "EQ-Bench(v2)": "EQ-Bench v2",
-#     },
-#     inplace=True,
-# )
-
-# col1, col2, col3 = st.columns(3)
-
-# with col1:
-#     st.header("‎ ‎ ‎ ‎ ‎ ‎ ‎ ‎ Agree")
-#     st.dataframe(df.query("Z_Score>=0"), hide_index=True)
-
-# with col2:
-#     st.header("‎ ‎‎  ‎ Disagree")
-#     st.dataframe(df.query("Z_Score<0").sort_values("Z_Score"), hide_index=True)
-
-# with col3:
-#     st.header("‎ ‎‎  ‎ Configs")
-#     # st.selectbox(label="Reference Benchmarks", options=["LMSys Arena"])
-#     options = st.multiselect(
-#         "Reference Benchmarks",
-#         ["LMSys Arena", "Open Compass", "Yellow", "Red", "Blue"],
-#         ["LMSys Arena", "Open Compass"],
-#     )
-#     st.selectbox(label="# models compared", options=[20])
-#     st.selectbox(label="Model Select Strategy", options=["Random"])
-#     st.write("‎‎‎‎‎‎‎")
-#     st.button("Upload a new benchmark")
+```python
+all_agreements = tester.all_vs_all_agreement_testing(allbench)
+reporter.draw_agreements(all_agreements)
+```
+""")

assets/combined_holistic.csv

@@ -1,825 +0,0 @@
-,model,score,scenario,source,aggragated_from
-0,gpt-4-turbo-2024-04-09,82.6,arena-hard,arena_hard_2404,[]
-1,gpt-4-0125-preview,78.0,arena-hard,arena_hard_2404,[]
-2,gemini-1.5-pro-api-preview,72.0,arena-hard,arena_hard_2404,[]
-3,yi-large,63.7,arena-hard,arena_hard_2404,[]
-4,claude-3-opus-20240229,60.4,arena-hard,arena_hard_2404,[]
-5,glm-4,55.7,arena-hard,arena_hard_2404,[]
-6,gpt-4-0314,50.0,arena-hard,arena_hard_2404,[]
-7,gemini-1.5-flash-api-preview,49.6,arena-hard,arena_hard_2404,[]
-8,claude-3-sonnet-20240229,46.8,arena-hard,arena_hard_2404,[]
-9,claude-3-haiku-20240307,41.5,arena-hard,arena_hard_2404,[]
-10,llama-3-70b-chat-hf,41.1,arena-hard,arena_hard_2404,[]
-11,gpt-4-0613,37.9,arena-hard,arena_hard_2404,[]
-12,mistral-large-2402,37.7,arena-hard,arena_hard_2404,[]
-13,mixtral-8x22b-instruct-v0.1,36.4,arena-hard,arena_hard_2404,[]
-14,qwen1.5-72b-chat,36.1,arena-hard,arena_hard_2404,[]
-15,command-r-plus,33.1,arena-hard,arena_hard_2404,[]
-16,mistral-medium,31.9,arena-hard,arena_hard_2404,[]
-17,mistral-next,27.4,arena-hard,arena_hard_2404,[]
-18,gpt-3.5-turbo-0613,24.8,arena-hard,arena_hard_2404,[]
-19,claude-2.0,24.0,arena-hard,arena_hard_2404,[]
-20,dbrx-instructruct,23.9,arena-hard,arena_hard_2404,[]
-21,mixtral-8x7b-instruct-v0.1,23.4,arena-hard,arena_hard_2404,[]
-22,gpt-3.5-turbo-0125,23.3,arena-hard,arena_hard_2404,[]
-23,yi-34b-chat,23.1,arena-hard,arena_hard_2404,[]
-24,starling-lm-7b-beta,23.0,arena-hard,arena_hard_2404,[]
-25,claude-2.1,22.8,arena-hard,arena_hard_2404,[]
-26,snorkel-mistral-pairrm-dpo,20.7,arena-hard,arena_hard_2404,[]
-27,llama-3-8b-chat-hf,20.6,arena-hard,arena_hard_2404,[]
-28,gpt-3.5-turbo-1106,18.9,arena-hard,arena_hard_2404,[]
-29,gpt-3.5-turbo-0301,18.1,arena-hard,arena_hard_2404,[]
-30,gemini-1.0-pro,17.8,arena-hard,arena_hard_2404,[]
-31,snowflake-arctic-instruct,17.6,arena-hard,arena_hard_2404,[]
-32,command-r,17.0,arena-hard,arena_hard_2404,[]
-33,phi-3-mini-128k-instruct,15.4,arena-hard,arena_hard_2404,[]
-34,tulu-2-dpo-70b,15.0,arena-hard,arena_hard_2404,[]
-35,starling-lm-7b-alpha,12.8,arena-hard,arena_hard_2404,[]
-36,mistral-7b-instruct,12.6,arena-hard,arena_hard_2404,[]
-37,gemma-1.1-7b-it,12.1,arena-hard,arena_hard_2404,[]
-38,llama-2-70b-chat-hf,11.6,arena-hard,arena_hard_2404,[]
-39,vicuna-33b-v1.3,8.6,arena-hard,arena_hard_2404,[]
-40,gemma-7b-it,7.5,arena-hard,arena_hard_2404,[]
-41,llama-2-7b-chat-hf,4.6,arena-hard,arena_hard_2404,[]
-42,gemma-1.1-2b-it,3.4,arena-hard,arena_hard_2404,[]
-43,gemma-2b-it,3.0,arena-hard,arena_hard_2404,[]
-0,gpt-4o-2024-05-13,64.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-1,claude-3-opus,63.5,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-2,gpt-4-turbo-2024-04-09,62.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-3,gemini-1.5-pro-api-0409,58.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-4,yi-large-preview,56.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-5,llama-3-70b-instruct,55.9,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-6,qwen-max-0428,55.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-7,claude-3-sonnet,54.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-8,reka-core-20240415,52.9,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-9,mammoth2-8x7b-plus,51.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-10,deepseek-v2,51.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-11,command-r-plus,51.4,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-12,yi-1.5-34b-chat,51.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-13,mistral-large,50.3,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-14,qwen1.5-72b-chat,48.3,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-15,mistral-medium,47.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-16,gemini-1.0-pro,46.4,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-17,reka-flash-20240226,46.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-18,mistral-small,46.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-19,llama-3-8b-instruct,45.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-20,command-r,45.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-21,qwen1.5-32b-chat,43.3,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-22,gpt-3.5-turbo-0125,43.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-23,claude-3-haiku,42.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-24,yi-34b-chat,42.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-25,mixtral-8x7b-instruct-v0.1,42.5,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-26,starling-lm-7b-beta,41.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-27,yi-1.5-9b-chat,40.9,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-28,gemma-1.1-7b-it,39.1,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-29,vicuna-33b-v1.3,38.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-30,llama-2-70b-chat,38.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-31,map-neo-instruct-v0.1,37.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-32,mistral-7b-instruct-v0.2,36.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-33,qwen1.5-7b-chat,35.5,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-34,reka-edge-20240208,32.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-35,zephyr-7b-beta,31.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-36,llama-2-7b-chat,30.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-37,yi-6b-chat,30.1,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-38,qwen1.5-moe-a2.7b-chat,29.1,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-39,gemma-1.1-2b-it,28.4,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-40,vicuna-7b-v1.5,27.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-41,olmo-7b-instruct,26.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-42,qwen1.5-4b-chat,24.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-43,jetmoe-8b-chat,24.3,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-44,mpt-7b-chat,23.8,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-45,llama-3-70b,54.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-46,qwen1.5-72b,41.9,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-47,yi-34b,47.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-48,qwen1.5-32b,41.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-49,mixtral-8x7b,40.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-50,llama-2-70b,41.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-51,qwen1.5-moe-a2.7b,33.5,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-52,qwen1.5-7b,33.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-53,llama-3-8b,31.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-54,mistral-7b,27.1,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-55,gemma-7b,32.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-56,yi-6b,30.4,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-57,qwen1.5-4b,23.5,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-58,jetmoe-8b,27.0,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-59,deepseek-7b,21.7,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-60,phi-2,21.9,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-61,deepseekmoe-16b,24.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-62,llama-2-7b,22.1,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-63,gemma-2b,22.6,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-64,olmo-7b,21.2,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-65,mpt-7b,17.4,mixeval-hard,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-66,gpt-4o-2024-05-13,87.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-67,claude-3-opus,88.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-68,gpt-4-turbo-2024-04-09,88.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-69,gemini-1.5-pro-api-0409,84.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-70,yi-large-preview,84.4,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-71,llama-3-70b-instruct,84.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-72,qwen-max-0428,86.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-73,claude-3-sonnet,81.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-74,reka-core-20240415,83.3,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-75,mammoth2-8x7b-plus,81.5,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-76,deepseek-v2,83.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-77,command-r-plus,81.5,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-78,yi-1.5-34b-chat,81.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-79,mistral-large,84.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-80,qwen1.5-72b-chat,84.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-81,mistral-medium,81.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-82,gemini-1.0-pro,78.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-83,reka-flash-20240226,79.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-84,mistral-small,81.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-85,llama-3-8b-instruct,75.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-86,command-r,77.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-87,qwen1.5-32b-chat,81.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-88,gpt-3.5-turbo-0125,79.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-89,claude-3-haiku,79.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-90,yi-34b-chat,80.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-91,mixtral-8x7b-instruct-v0.1,76.4,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-92,starling-lm-7b-beta,74.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-93,yi-1.5-9b-chat,74.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-94,gemma-1.1-7b-it,69.6,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-95,vicuna-33b-v1.3,66.3,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-96,llama-2-70b-chat,74.6,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-97,map-neo-instruct-v0.1,70.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-98,mistral-7b-instruct-v0.2,70.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-99,qwen1.5-7b-chat,71.4,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-100,reka-edge-20240208,68.5,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-101,zephyr-7b-beta,69.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-102,llama-2-7b-chat,61.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-103,yi-6b-chat,65.6,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-104,qwen1.5-moe-a2.7b-chat,69.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-105,gemma-1.1-2b-it,51.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-106,vicuna-7b-v1.5,60.3,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-107,olmo-7b-instruct,55.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-108,qwen1.5-4b-chat,57.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-109,jetmoe-8b-chat,51.6,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-110,mpt-7b-chat,43.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-111,llama-3-70b,82.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-112,qwen1.5-72b,79.5,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-113,yi-34b,78.3,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-114,qwen1.5-32b,77.6,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-115,mixtral-8x7b,74.0,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-116,llama-2-70b,73.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-117,qwen1.5-moe-a2.7b,70.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-118,qwen1.5-7b,68.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-119,llama-3-8b,65.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-120,mistral-7b,64.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-121,gemma-7b,64.7,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-122,yi-6b,63.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-123,qwen1.5-4b,58.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-124,jetmoe-8b,57.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-125,deepseek-7b,52.2,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-126,phi-2,51.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-127,deepseekmoe-16b,51.4,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-128,llama-2-7b,43.1,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-129,gemma-2b,38.9,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-130,olmo-7b,31.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-131,mpt-7b,30.8,mixeval,mixeval_240601,"['triviaqa-mixed', 'mmlu-mixed', 'drop-mixed', 'hellaswag-mixed', 'commonsenseqa-mixed', 'triviaqa-hard-mixed', 'mmlu-hard-mixed', 'drop-hard-mixed', 'boolq-mixed']"
-264,gpt-4o-2024-05-13,85.4,mmlu-mixed,mixeval_240601,[]
-265,claude-3-opus,83.2,mmlu-mixed,mixeval_240601,[]
-266,gpt-4-turbo-2024-04-09,82.8,mmlu-mixed,mixeval_240601,[]
-267,gemini-1.5-pro-api-0409,79.2,mmlu-mixed,mixeval_240601,[]
-268,yi-large-preview,80.9,mmlu-mixed,mixeval_240601,[]
-269,llama-3-70b-instruct,80.5,mmlu-mixed,mixeval_240601,[]
-270,qwen-max-0428,80.6,mmlu-mixed,mixeval_240601,[]
-271,claude-3-sonnet,74.7,mmlu-mixed,mixeval_240601,[]
-272,reka-core-20240415,79.3,mmlu-mixed,mixeval_240601,[]
-273,mammoth2-8x7b-plus,74.5,mmlu-mixed,mixeval_240601,[]
-274,deepseek-v2,77.3,mmlu-mixed,mixeval_240601,[]
-275,command-r-plus,78.9,mmlu-mixed,mixeval_240601,[]
-276,yi-1.5-34b-chat,76.4,mmlu-mixed,mixeval_240601,[]
-277,mistral-large,80.2,mmlu-mixed,mixeval_240601,[]
-278,qwen1.5-72b-chat,80.1,mmlu-mixed,mixeval_240601,[]
-279,mistral-medium,76.3,mmlu-mixed,mixeval_240601,[]
-280,gemini-1.0-pro,74.9,mmlu-mixed,mixeval_240601,[]
-281,reka-flash-20240226,75.4,mmlu-mixed,mixeval_240601,[]
-282,mistral-small,75.2,mmlu-mixed,mixeval_240601,[]
-283,llama-3-8b-instruct,71.9,mmlu-mixed,mixeval_240601,[]
-284,command-r,75.0,mmlu-mixed,mixeval_240601,[]
-285,qwen1.5-32b-chat,78.0,mmlu-mixed,mixeval_240601,[]
-286,gpt-3.5-turbo-0125,74.5,mmlu-mixed,mixeval_240601,[]
-287,claude-3-haiku,76.1,mmlu-mixed,mixeval_240601,[]
-288,yi-34b-chat,73.6,mmlu-mixed,mixeval_240601,[]
-289,mixtral-8x7b-instruct-v0.1,72.0,mmlu-mixed,mixeval_240601,[]
-290,starling-lm-7b-beta,69.0,mmlu-mixed,mixeval_240601,[]
-291,yi-1.5-9b-chat,72.6,mmlu-mixed,mixeval_240601,[]
-292,gemma-1.1-7b-it,66.9,mmlu-mixed,mixeval_240601,[]
-293,vicuna-33b-v1.3,59.2,mmlu-mixed,mixeval_240601,[]
-294,llama-2-70b-chat,69.8,mmlu-mixed,mixeval_240601,[]
-295,map-neo-instruct-v0.1,66.7,mmlu-mixed,mixeval_240601,[]
-296,mistral-7b-instruct-v0.2,67.3,mmlu-mixed,mixeval_240601,[]
-297,qwen1.5-7b-chat,68.7,mmlu-mixed,mixeval_240601,[]
-298,reka-edge-20240208,63.6,mmlu-mixed,mixeval_240601,[]
-299,zephyr-7b-beta,64.9,mmlu-mixed,mixeval_240601,[]
-300,llama-2-7b-chat,59.4,mmlu-mixed,mixeval_240601,[]
-301,yi-6b-chat,65.4,mmlu-mixed,mixeval_240601,[]
-302,qwen1.5-moe-a2.7b-chat,69.5,mmlu-mixed,mixeval_240601,[]
-303,gemma-1.1-2b-it,51.5,mmlu-mixed,mixeval_240601,[]
-304,vicuna-7b-v1.5,58.7,mmlu-mixed,mixeval_240601,[]
-305,olmo-7b-instruct,57.1,mmlu-mixed,mixeval_240601,[]
-306,qwen1.5-4b-chat,61.4,mmlu-mixed,mixeval_240601,[]
-307,jetmoe-8b-chat,58.5,mmlu-mixed,mixeval_240601,[]
-308,mpt-7b-chat,37.8,mmlu-mixed,mixeval_240601,[]
-309,llama-3-70b,79.8,mmlu-mixed,mixeval_240601,[]
-310,qwen1.5-72b,78.8,mmlu-mixed,mixeval_240601,[]
-311,yi-34b,79.3,mmlu-mixed,mixeval_240601,[]
-312,qwen1.5-32b,77.2,mmlu-mixed,mixeval_240601,[]
-313,mixtral-8x7b,71.6,mmlu-mixed,mixeval_240601,[]
-314,llama-2-70b,70.8,mmlu-mixed,mixeval_240601,[]
-315,qwen1.5-moe-a2.7b,69.4,mmlu-mixed,mixeval_240601,[]
-316,qwen1.5-7b,67.0,mmlu-mixed,mixeval_240601,[]
-317,llama-3-8b,69.5,mmlu-mixed,mixeval_240601,[]
-318,mistral-7b,68.5,mmlu-mixed,mixeval_240601,[]
-319,gemma-7b,67.4,mmlu-mixed,mixeval_240601,[]
-320,yi-6b,71.2,mmlu-mixed,mixeval_240601,[]
-321,qwen1.5-4b,59.6,mmlu-mixed,mixeval_240601,[]
-322,jetmoe-8b,55.3,mmlu-mixed,mixeval_240601,[]
-323,deepseek-7b,53.3,mmlu-mixed,mixeval_240601,[]
-324,phi-2,62.5,mmlu-mixed,mixeval_240601,[]
-325,deepseekmoe-16b,49.9,mmlu-mixed,mixeval_240601,[]
-326,llama-2-7b,40.8,mmlu-mixed,mixeval_240601,[]
-327,gemma-2b,37.4,mmlu-mixed,mixeval_240601,[]
-328,olmo-7b,29.7,mmlu-mixed,mixeval_240601,[]
-329,mpt-7b,30.9,mmlu-mixed,mixeval_240601,[]
-594,gpt-4o-2024-05-13,57.1,mmlu-hard-mixed,mixeval_240601,[]
-595,claude-3-opus,55.0,mmlu-hard-mixed,mixeval_240601,[]
-596,gpt-4-turbo-2024-04-09,45.5,mmlu-hard-mixed,mixeval_240601,[]
-597,gemini-1.5-pro-api-0409,44.6,mmlu-hard-mixed,mixeval_240601,[]
-598,yi-large-preview,48.5,mmlu-hard-mixed,mixeval_240601,[]
-599,llama-3-70b-instruct,46.3,mmlu-hard-mixed,mixeval_240601,[]
-600,qwen-max-0428,41.6,mmlu-hard-mixed,mixeval_240601,[]
-601,claude-3-sonnet,40.7,mmlu-hard-mixed,mixeval_240601,[]
-602,reka-core-20240415,46.3,mmlu-hard-mixed,mixeval_240601,[]
-603,mammoth2-8x7b-plus,41.1,mmlu-hard-mixed,mixeval_240601,[]
-604,deepseek-v2,42.0,mmlu-hard-mixed,mixeval_240601,[]
-605,command-r-plus,42.0,mmlu-hard-mixed,mixeval_240601,[]
-606,yi-1.5-34b-chat,38.1,mmlu-hard-mixed,mixeval_240601,[]
-607,mistral-large,42.4,mmlu-hard-mixed,mixeval_240601,[]
-608,qwen1.5-72b-chat,37.7,mmlu-hard-mixed,mixeval_240601,[]
-609,mistral-medium,38.5,mmlu-hard-mixed,mixeval_240601,[]
-610,gemini-1.0-pro,35.5,mmlu-hard-mixed,mixeval_240601,[]
-611,reka-flash-20240226,34.6,mmlu-hard-mixed,mixeval_240601,[]
-612,mistral-small,33.8,mmlu-hard-mixed,mixeval_240601,[]
-613,llama-3-8b-instruct,40.7,mmlu-hard-mixed,mixeval_240601,[]
-614,command-r,39.0,mmlu-hard-mixed,mixeval_240601,[]
-615,qwen1.5-32b-chat,29.9,mmlu-hard-mixed,mixeval_240601,[]
-616,gpt-3.5-turbo-0125,35.1,mmlu-hard-mixed,mixeval_240601,[]
-617,claude-3-haiku,30.7,mmlu-hard-mixed,mixeval_240601,[]
-618,yi-34b-chat,29.9,mmlu-hard-mixed,mixeval_240601,[]
-619,mixtral-8x7b-instruct-v0.1,37.2,mmlu-hard-mixed,mixeval_240601,[]
-620,starling-lm-7b-beta,34.2,mmlu-hard-mixed,mixeval_240601,[]
-621,yi-1.5-9b-chat,36.8,mmlu-hard-mixed,mixeval_240601,[]
-622,gemma-1.1-7b-it,39.0,mmlu-hard-mixed,mixeval_240601,[]
-623,vicuna-33b-v1.3,39.4,mmlu-hard-mixed,mixeval_240601,[]
-624,llama-2-70b-chat,27.7,mmlu-hard-mixed,mixeval_240601,[]
-625,map-neo-instruct-v0.1,32.5,mmlu-hard-mixed,mixeval_240601,[]
-626,mistral-7b-instruct-v0.2,29.4,mmlu-hard-mixed,mixeval_240601,[]
-627,qwen1.5-7b-chat,29.0,mmlu-hard-mixed,mixeval_240601,[]
-628,reka-edge-20240208,26.4,mmlu-hard-mixed,mixeval_240601,[]
-629,zephyr-7b-beta,24.2,mmlu-hard-mixed,mixeval_240601,[]
-630,llama-2-7b-chat,30.3,mmlu-hard-mixed,mixeval_240601,[]
-631,yi-6b-chat,26.8,mmlu-hard-mixed,mixeval_240601,[]
-632,qwen1.5-moe-a2.7b-chat,26.8,mmlu-hard-mixed,mixeval_240601,[]
-633,gemma-1.1-2b-it,30.3,mmlu-hard-mixed,mixeval_240601,[]
-634,vicuna-7b-v1.5,23.4,mmlu-hard-mixed,mixeval_240601,[]
-635,olmo-7b-instruct,27.3,mmlu-hard-mixed,mixeval_240601,[]
-636,qwen1.5-4b-chat,17.3,mmlu-hard-mixed,mixeval_240601,[]
-637,jetmoe-8b-chat,25.5,mmlu-hard-mixed,mixeval_240601,[]
-638,mpt-7b-chat,24.7,mmlu-hard-mixed,mixeval_240601,[]
-639,llama-3-70b,39.8,mmlu-hard-mixed,mixeval_240601,[]
-640,qwen1.5-72b,42.4,mmlu-hard-mixed,mixeval_240601,[]
-641,yi-34b,42.4,mmlu-hard-mixed,mixeval_240601,[]
-642,qwen1.5-32b,37.2,mmlu-hard-mixed,mixeval_240601,[]
-643,mixtral-8x7b,34.6,mmlu-hard-mixed,mixeval_240601,[]
-644,llama-2-70b,29.0,mmlu-hard-mixed,mixeval_240601,[]
-645,qwen1.5-moe-a2.7b,30.7,mmlu-hard-mixed,mixeval_240601,[]
-646,qwen1.5-7b,28.6,mmlu-hard-mixed,mixeval_240601,[]
-647,llama-3-8b,38.5,mmlu-hard-mixed,mixeval_240601,[]
-648,mistral-7b,27.7,mmlu-hard-mixed,mixeval_240601,[]
-649,gemma-7b,28.1,mmlu-hard-mixed,mixeval_240601,[]
-650,yi-6b,37.2,mmlu-hard-mixed,mixeval_240601,[]
-651,qwen1.5-4b,22.9,mmlu-hard-mixed,mixeval_240601,[]
-652,jetmoe-8b,27.3,mmlu-hard-mixed,mixeval_240601,[]
-653,deepseek-7b,26.4,mmlu-hard-mixed,mixeval_240601,[]
-654,phi-2,29.0,mmlu-hard-mixed,mixeval_240601,[]
-655,deepseekmoe-16b,30.7,mmlu-hard-mixed,mixeval_240601,[]
-656,llama-2-7b,24.7,mmlu-hard-mixed,mixeval_240601,[]
-657,gemma-2b,27.3,mmlu-hard-mixed,mixeval_240601,[]
-658,olmo-7b,25.1,mmlu-hard-mixed,mixeval_240601,[]
-659,mpt-7b,24.2,mmlu-hard-mixed,mixeval_240601,[]
-593,gpt-4-0314,0.57,agieval,BLZ_240312,[]
-594,gpt-4-0613,0.57,agieval,BLZ_240312,[]
-596,claude-1,0.49700000000000005,agieval,BLZ_240312,[]
-601,mixtral-8x7b-instruct-v0.1,0.45299999999999996,agieval,BLZ_240312,[]
-602,yi-34b-chat,0.508,agieval,BLZ_240312,[]
-605,gpt-3.5-turbo-0314,0.43200000000000005,agieval,BLZ_240312,[]
-608,vicuna-33b,0.373,agieval,BLZ_240312,[]
-609,starling-lm-7b-alpha,0.401,agieval,BLZ_240312,[]
-611,llama-2-70b-chat,0.45,agieval,BLZ_240312,[]
-613,openhermes-2.5-mistral-7b,0.43,agieval,BLZ_240312,[]
-614,openchat-3.5,0.42700000000000005,agieval,BLZ_240312,[]
-617,solar-10.7b-instruct-v1.0,0.47600000000000003,agieval,BLZ_240312,[]
-618,dolphin-2.2.1-mistral-7b,0.392,agieval,BLZ_240312,[]
-620,zephyr-7b-beta,0.406,agieval,BLZ_240312,[]
-623,llama-2-13b-chat,0.336,agieval,BLZ_240312,[]
-624,vicuna-13b,0.368,agieval,BLZ_240312,[]
-626,zephyr-7b-alpha,0.38,agieval,BLZ_240312,[]
-627,qwen-14b-chat,0.396,agieval,BLZ_240312,[]
-630,llama-2-7b-chat,0.29600000000000004,agieval,BLZ_240312,[]
-632,mistral-7b-instruct-v0.1,0.335,agieval,BLZ_240312,[]
-634,vicuna-7b,0.314,agieval,BLZ_240312,[]
-636,chatglm3-6b,0.414,agieval,BLZ_240312,[]
-643,chatglm-6b,0.325,agieval,BLZ_240312,[]
-647,llama-13b,0.205,agieval,BLZ_240312,[]
-886,gpt-4-1106-preview,0.977,alpacav1,BLZ_240312,[]
-888,gpt-4-0314,0.9528,alpacav1,BLZ_240312,[]
-889,gpt-4-0613,0.9528,alpacav1,BLZ_240312,[]
-890,mistral-medium,0.9682999999999999,alpacav1,BLZ_240312,[]
-891,claude-1,0.8839,alpacav1,BLZ_240312,[]
-892,claude-2.0,0.9136,alpacav1,BLZ_240312,[]
-893,gemini-pro-dev-api,0.7966,alpacav1,BLZ_240312,[]
-894,claude-2.1,0.8708,alpacav1,BLZ_240312,[]
-895,gpt-3.5-turbo-0613,0.8937,alpacav1,BLZ_240312,[]
-896,mixtral-8x7b-instruct-v0.1,0.9478,alpacav1,BLZ_240312,[]
-897,yi-34b-chat,0.9408,alpacav1,BLZ_240312,[]
-898,gemini-pro,0.7966,alpacav1,BLZ_240312,[]
-900,gpt-3.5-turbo-0314,0.8937,alpacav1,BLZ_240312,[]
-902,tulu-2-dpo-70b,0.9503,alpacav1,BLZ_240312,[]
-903,vicuna-33b,0.8898999999999999,alpacav1,BLZ_240312,[]
-904,starling-lm-7b-alpha,0.9198999999999999,alpacav1,BLZ_240312,[]
-906,llama-2-70b-chat,0.9266,alpacav1,BLZ_240312,[]
-909,openchat-3.5,0.8851,alpacav1,BLZ_240312,[]
-911,gpt-3.5-turbo-1106,0.8626,alpacav1,BLZ_240312,[]
-914,wizardlm-13b-v1.2,0.8917,alpacav1,BLZ_240312,[]
-915,zephyr-7b-beta,0.9059999999999999,alpacav1,BLZ_240312,[]
-918,llama-2-13b-chat,0.8109000000000001,alpacav1,BLZ_240312,[]
-921,zephyr-7b-alpha,0.8576,alpacav1,BLZ_240312,[]
-924,guanaco-33b,0.6596,alpacav1,BLZ_240312,[]
-925,llama-2-7b-chat,0.7137,alpacav1,BLZ_240312,[]
-934,chatglm2-6b,0.47130000000000005,alpacav1,BLZ_240312,[]
-937,openassistant-pythia-12b,0.2596,alpacav1,BLZ_240312,[]
-827,gpt-4-1106-preview,0.5,alpacav2,BLZ_240312,[]
-829,gpt-4-0314,0.221,alpacav2,BLZ_240312,[]
-830,gpt-4-0613,0.158,alpacav2,BLZ_240312,[]
-831,mistral-medium,0.21899999999999997,alpacav2,BLZ_240312,[]
-832,claude-1,0.17,alpacav2,BLZ_240312,[]
-833,claude-2.0,0.172,alpacav2,BLZ_240312,[]
-834,gemini-pro-dev-api,0.16899999999999998,alpacav2,BLZ_240312,[]
-835,claude-2.1,0.157,alpacav2,BLZ_240312,[]
-836,gpt-3.5-turbo-0613,0.141,alpacav2,BLZ_240312,[]
-837,mixtral-8x7b-instruct-v0.1,0.183,alpacav2,BLZ_240312,[]
-838,yi-34b-chat,0.297,alpacav2,BLZ_240312,[]
-839,gemini-pro,0.16899999999999998,alpacav2,BLZ_240312,[]
-840,claude-instant-1,0.161,alpacav2,BLZ_240312,[]
-841,gpt-3.5-turbo-0314,0.096,alpacav2,BLZ_240312,[]
-842,wizardlm-70b-v1.0,0.14400000000000002,alpacav2,BLZ_240312,[]
-843,tulu-2-dpo-70b,0.16,alpacav2,BLZ_240312,[]
-844,vicuna-33b,0.127,alpacav2,BLZ_240312,[]
-845,starling-lm-7b-alpha,0.142,alpacav2,BLZ_240312,[]
-846,deepseek-llm-67b-chat,0.121,alpacav2,BLZ_240312,[]
-847,llama-2-70b-chat,0.139,alpacav2,BLZ_240312,[]
-849,openhermes-2.5-mistral-7b,0.10300000000000001,alpacav2,BLZ_240312,[]
-852,gpt-3.5-turbo-1106,0.092,alpacav2,BLZ_240312,[]
-854,dolphin-2.2.1-mistral-7b,0.09,alpacav2,BLZ_240312,[]
-855,wizardlm-13b-v1.2,0.12,alpacav2,BLZ_240312,[]
-856,zephyr-7b-beta,0.11,alpacav2,BLZ_240312,[]
-859,llama-2-13b-chat,0.077,alpacav2,BLZ_240312,[]
-860,vicuna-13b,0.067,alpacav2,BLZ_240312,[]
-862,zephyr-7b-alpha,0.084,alpacav2,BLZ_240312,[]
-863,qwen-14b-chat,0.075,alpacav2,BLZ_240312,[]
-865,guanaco-33b,0.05,alpacav2,BLZ_240312,[]
-866,llama-2-7b-chat,0.0496,alpacav2,BLZ_240312,[]
-870,vicuna-7b,0.048,alpacav2,BLZ_240312,[]
-875,chatglm2-6b,0.027999999999999997,alpacav2,BLZ_240312,[]
-878,openassistant-pythia-12b,0.018000000000000002,alpacav2,BLZ_240312,[]
-1299,gpt-4-1106-preview,0.32799999999999996,alpacaeval2-lc,BLZ_240312,[]
-1301,gpt-4-0314,0.21600000000000003,alpacaeval2-lc,BLZ_240312,[]
-1302,gpt-4-0613,0.18600000000000003,alpacaeval2-lc,BLZ_240312,[]
-1303,mistral-medium,0.196,alpacaeval2-lc,BLZ_240312,[]
-1304,claude-1,0.21100000000000002,alpacaeval2-lc,BLZ_240312,[]
-1305,claude-2.0,0.21600000000000003,alpacaeval2-lc,BLZ_240312,[]
-1306,gemini-pro-dev-api,0.172,alpacaeval2-lc,BLZ_240312,[]
-1307,claude-2.1,0.193,alpacaeval2-lc,BLZ_240312,[]
-1308,gpt-3.5-turbo-0613,0.14300000000000002,alpacaeval2-lc,BLZ_240312,[]
-1309,mixtral-8x7b-instruct-v0.1,0.168,alpacaeval2-lc,BLZ_240312,[]
-1310,yi-34b-chat,0.188,alpacaeval2-lc,BLZ_240312,[]
-1312,claude-instant-1,0.195,alpacaeval2-lc,BLZ_240312,[]
-1313,gpt-3.5-turbo-0314,0.156,alpacaeval2-lc,BLZ_240312,[]
-1314,wizardlm-70b-v1.0,0.125,alpacaeval2-lc,BLZ_240312,[]
-1315,tulu-2-dpo-70b,0.151,alpacaeval2-lc,BLZ_240312,[]
-1316,vicuna-33b,0.115,alpacaeval2-lc,BLZ_240312,[]
-1317,starling-lm-7b-alpha,0.10099999999999999,alpacaeval2-lc,BLZ_240312,[]
-1318,deepseek-llm-67b-chat,0.141,alpacaeval2-lc,BLZ_240312,[]
-1319,llama-2-70b-chat,0.10400000000000001,alpacaeval2-lc,BLZ_240312,[]
-1321,openhermes-2.5-mistral-7b,0.126,alpacaeval2-lc,BLZ_240312,[]
-1324,gpt-3.5-turbo-1106,0.155,alpacaeval2-lc,BLZ_240312,[]
-1326,dolphin-2.2.1-mistral-7b,0.10800000000000001,alpacaeval2-lc,BLZ_240312,[]
-1327,wizardlm-13b-v1.2,0.099,alpacaeval2-lc,BLZ_240312,[]
-1328,zephyr-7b-beta,0.102,alpacaeval2-lc,BLZ_240312,[]
-1331,llama-2-13b-chat,0.068,alpacaeval2-lc,BLZ_240312,[]
-1332,vicuna-13b,0.085,alpacaeval2-lc,BLZ_240312,[]
-1334,zephyr-7b-alpha,0.086,alpacaeval2-lc,BLZ_240312,[]
-1335,qwen-14b-chat,0.1,alpacaeval2-lc,BLZ_240312,[]
-1338,llama-2-7b-chat,0.045,alpacaeval2-lc,BLZ_240312,[]
-1342,vicuna-7b,0.06,alpacaeval2-lc,BLZ_240312,[]
-0,gpt-4-0125-preview,1.0,arena-elo,BLZ_240312,[]
-1,gpt-4-1106-preview,0.9992019154030327,arena-elo,BLZ_240312,[]
-2,bard-gemini-pro,0.9768555466879489,arena-elo,BLZ_240312,[]
-3,gpt-4-0314,0.9497206703910615,arena-elo,BLZ_240312,[]
-4,gpt-4-0613,0.9273743016759777,arena-elo,BLZ_240312,[]
-5,mistral-medium,0.9177972865123704,arena-elo,BLZ_240312,[]
-6,claude-1,0.9169992019154031,arena-elo,BLZ_240312,[]
-7,claude-2.0,0.9034317637669593,arena-elo,BLZ_240312,[]
-8,gemini-pro-dev-api,0.8938547486033519,arena-elo,BLZ_240312,[]
-9,claude-2.1,0.8930566640063847,arena-elo,BLZ_240312,[]
-10,gpt-3.5-turbo-0613,0.8922585794094174,arena-elo,BLZ_240312,[]
-11,mixtral-8x7b-instruct-v0.1,0.8922585794094174,arena-elo,BLZ_240312,[]
-12,yi-34b-chat,0.8898643256185156,arena-elo,BLZ_240312,[]
-13,gemini-pro,0.8890662410215483,arena-elo,BLZ_240312,[]
-14,claude-instant-1,0.8850758180367119,arena-elo,BLZ_240312,[]
-15,gpt-3.5-turbo-0314,0.8818834796488427,arena-elo,BLZ_240312,[]
-16,wizardlm-70b-v1.0,0.8818834796488427,arena-elo,BLZ_240312,[]
-17,tulu-2-dpo-70b,0.8810853950518756,arena-elo,BLZ_240312,[]
-18,vicuna-33b,0.8723064644852354,arena-elo,BLZ_240312,[]
-19,starling-lm-7b-alpha,0.8699122106943336,arena-elo,BLZ_240312,[]
-20,deepseek-llm-67b-chat,0.8635275339185954,arena-elo,BLZ_240312,[]
-21,llama-2-70b-chat,0.8635275339185954,arena-elo,BLZ_240312,[]
-22,nv-llama2-70b-steerlm-chat,0.8603351955307262,arena-elo,BLZ_240312,[]
-23,openhermes-2.5-mistral-7b,0.8603351955307262,arena-elo,BLZ_240312,[]
-24,openchat-3.5,0.8587390263367917,arena-elo,BLZ_240312,[]
-25,pplx-70b-online,0.8587390263367917,arena-elo,BLZ_240312,[]
-26,gpt-3.5-turbo-1106,0.8547486033519553,arena-elo,BLZ_240312,[]
-27,solar-10.7b-instruct-v1.0,0.8499600957701516,arena-elo,BLZ_240312,[]
-28,dolphin-2.2.1-mistral-7b,0.8499600957701516,arena-elo,BLZ_240312,[]
-29,wizardlm-13b-v1.2,0.8443735035913806,arena-elo,BLZ_240312,[]
-30,zephyr-7b-beta,0.8387869114126097,arena-elo,BLZ_240312,[]
-31,mpt-30b-chat,0.8332003192338387,arena-elo,BLZ_240312,[]
-32,codellama-34b-instruct,0.8324022346368715,arena-elo,BLZ_240312,[]
-33,llama-2-13b-chat,0.8316041500399042,arena-elo,BLZ_240312,[]
-34,vicuna-13b,0.8300079808459697,arena-elo,BLZ_240312,[]
-35,pplx-7b-online,0.8284118116520351,arena-elo,BLZ_240312,[]
-36,zephyr-7b-alpha,0.8276137270550679,arena-elo,BLZ_240312,[]
-37,qwen-14b-chat,0.825219473264166,arena-elo,BLZ_240312,[]
-38,falcon-180b-chat,0.8236233040702314,arena-elo,BLZ_240312,[]
-39,guanaco-33b,0.8236233040702314,arena-elo,BLZ_240312,[]
-40,llama-2-7b-chat,0.8172386272944933,arena-elo,BLZ_240312,[]
-41,stripedhyena-nous-7b,0.8140462889066241,arena-elo,BLZ_240312,[]
-42,mistral-7b-instruct-v0.1,0.8028731045490822,arena-elo,BLZ_240312,[]
-43,palm-chat-bison-001,0.8028731045490822,arena-elo,BLZ_240312,[]
-44,vicuna-7b,0.8020750199521149,arena-elo,BLZ_240312,[]
-45,koala-13b,0.770949720670391,arena-elo,BLZ_240312,[]
-46,chatglm3-6b,0.7661612130885874,arena-elo,BLZ_240312,[]
-47,gpt4all-13b-snoozy,0.74780526735834,arena-elo,BLZ_240312,[]
-48,mpt-7b-chat,0.7430167597765364,arena-elo,BLZ_240312,[]
-49,chatglm2-6b,0.7422186751795691,arena-elo,BLZ_240312,[]
-50,rwkv-4-raven-14b,0.7382282521947326,arena-elo,BLZ_240312,[]
-51,alpaca-13b,0.7214684756584198,arena-elo,BLZ_240312,[]
-52,openassistant-pythia-12b,0.7158818834796489,arena-elo,BLZ_240312,[]
-53,chatglm-6b,0.704708699122107,arena-elo,BLZ_240312,[]
-54,fastchat-t5-3b,0.6975259377494014,arena-elo,BLZ_240312,[]
-55,stablelm-tuned-alpha-7b,0.6743814844373504,arena-elo,BLZ_240312,[]
-56,dolly-v2-12b,0.6568236233040702,arena-elo,BLZ_240312,[]
-57,llama-13b,0.6384676775738228,arena-elo,BLZ_240312,[]
-542,mixtral-8x7b-instruct-v0.1,0.7641,gpt4all,BLZ_240312,[]
-543,yi-34b-chat,0.7212999999999999,gpt4all,BLZ_240312,[]
-550,starling-lm-7b-alpha,0.7272,gpt4all,BLZ_240312,[]
-554,openhermes-2.5-mistral-7b,0.7312000000000001,gpt4all,BLZ_240312,[]
-555,openchat-3.5,0.7292000000000001,gpt4all,BLZ_240312,[]
-558,solar-10.7b-instruct-v1.0,0.7511,gpt4all,BLZ_240312,[]
-559,dolphin-2.2.1-mistral-7b,0.7223999999999999,gpt4all,BLZ_240312,[]
-561,zephyr-7b-beta,0.7182999999999999,gpt4all,BLZ_240312,[]
-565,vicuna-13b,0.631,gpt4all,BLZ_240312,[]
-567,zephyr-7b-alpha,0.7223999999999999,gpt4all,BLZ_240312,[]
-573,mistral-7b-instruct-v0.1,0.6795,gpt4all,BLZ_240312,[]
-575,vicuna-7b,0.61,gpt4all,BLZ_240312,[]
-576,koala-13b,0.62,gpt4all,BLZ_240312,[]
-578,gpt4all-13b-snoozy,0.653,gpt4all,BLZ_240312,[]
-579,mpt-7b-chat,0.648,gpt4all,BLZ_240312,[]
-583,openassistant-pythia-12b,0.61,gpt4all,BLZ_240312,[]
-585,fastchat-t5-3b,0.537,gpt4all,BLZ_240312,[]
-586,stablelm-tuned-alpha-7b,0.513,gpt4all,BLZ_240312,[]
-588,llama-13b,0.63,gpt4all,BLZ_240312,[]
-129,mixtral-8x7b-instruct-v0.1,0.7262000000000001,hugging-6,BLZ_240312,[]
-130,yi-34b-chat,0.6531999999999999,hugging-6,BLZ_240312,[]
-134,wizardlm-70b-v1.0,0.6125,hugging-6,BLZ_240312,[]
-135,tulu-2-dpo-70b,0.7376999999999999,hugging-6,BLZ_240312,[]
-136,vicuna-33b,0.585,hugging-6,BLZ_240312,[]
-137,starling-lm-7b-alpha,0.6713,hugging-6,BLZ_240312,[]
-139,llama-2-70b-chat,0.624,hugging-6,BLZ_240312,[]
-141,openhermes-2.5-mistral-7b,0.6152000000000001,hugging-6,BLZ_240312,[]
-142,openchat-3.5,0.6124,hugging-6,BLZ_240312,[]
-145,solar-10.7b-instruct-v1.0,0.742,hugging-6,BLZ_240312,[]
-146,dolphin-2.2.1-mistral-7b,0.6493000000000001,hugging-6,BLZ_240312,[]
-147,wizardlm-13b-v1.2,0.5476,hugging-6,BLZ_240312,[]
-148,zephyr-7b-beta,0.6195,hugging-6,BLZ_240312,[]
-149,mpt-30b-chat,0.5538000000000001,hugging-6,BLZ_240312,[]
-150,codellama-34b-instruct,0.5729,hugging-6,BLZ_240312,[]
-151,llama-2-13b-chat,0.5490999999999999,hugging-6,BLZ_240312,[]
-152,vicuna-13b,0.5539999999999999,hugging-6,BLZ_240312,[]
-154,zephyr-7b-alpha,0.595,hugging-6,BLZ_240312,[]
-156,falcon-180b-chat,0.6785,hugging-6,BLZ_240312,[]
-158,llama-2-7b-chat,0.5074000000000001,hugging-6,BLZ_240312,[]
-160,mistral-7b-instruct-v0.1,0.5496,hugging-6,BLZ_240312,[]
-162,vicuna-7b,0.521,hugging-6,BLZ_240312,[]
-176,yi-34bx2-moe-60b,0.7672,hugging-6,BLZ_240312,[]
-947,gpt-4-0314,0.93,llmonitor,BLZ_240312,[]
-948,gpt-4-0613,0.89,llmonitor,BLZ_240312,[]
-950,claude-1,0.66,llmonitor,BLZ_240312,[]
-951,claude-2.0,0.68,llmonitor,BLZ_240312,[]
-954,gpt-3.5-turbo-0613,0.81,llmonitor,BLZ_240312,[]
-958,claude-instant-1,0.6,llmonitor,BLZ_240312,[]
-959,gpt-3.5-turbo-0314,0.79,llmonitor,BLZ_240312,[]
-965,llama-2-70b-chat,0.6,llmonitor,BLZ_240312,[]
-975,mpt-30b-chat,0.4,llmonitor,BLZ_240312,[]
-976,codellama-34b-instruct,0.34,llmonitor,BLZ_240312,[]
-977,llama-2-13b-chat,0.5,llmonitor,BLZ_240312,[]
-978,vicuna-13b,0.5,llmonitor,BLZ_240312,[]
-982,falcon-180b-chat,0.67,llmonitor,BLZ_240312,[]
-983,guanaco-33b,0.43,llmonitor,BLZ_240312,[]
-984,llama-2-7b-chat,0.5,llmonitor,BLZ_240312,[]
-986,mistral-7b-instruct-v0.1,0.57,llmonitor,BLZ_240312,[]
-987,palm-chat-bison-001,0.57,llmonitor,BLZ_240312,[]
-988,vicuna-7b,0.41,llmonitor,BLZ_240312,[]
-989,koala-13b,0.31,llmonitor,BLZ_240312,[]
-992,mpt-7b-chat,0.43,llmonitor,BLZ_240312,[]
-1000,dolly-v2-12b,0.23,llmonitor,BLZ_240312,[]
-59,gpt-4-0125-preview,0.0929,mt-bench,BLZ_240312,[]
-60,gpt-4-1106-preview,0.0932,mt-bench,BLZ_240312,[]
-62,gpt-4-0314,0.08960000000000001,mt-bench,BLZ_240312,[]
-63,gpt-4-0613,0.09179999999999999,mt-bench,BLZ_240312,[]
-64,mistral-medium,0.0861,mt-bench,BLZ_240312,[]
-65,claude-1,0.079,mt-bench,BLZ_240312,[]
-66,claude-2.0,0.0806,mt-bench,BLZ_240312,[]
-67,gemini-pro-dev-api,0.08039999999999999,mt-bench,BLZ_240312,[]
-68,claude-2.1,0.0818,mt-bench,BLZ_240312,[]
-69,gpt-3.5-turbo-0613,0.0839,mt-bench,BLZ_240312,[]
-70,mixtral-8x7b-instruct-v0.1,0.083,mt-bench,BLZ_240312,[]
-71,yi-34b-chat,0.07769999999999999,mt-bench,BLZ_240312,[]
-72,gemini-pro,0.08039999999999999,mt-bench,BLZ_240312,[]
-73,claude-instant-1,0.0785,mt-bench,BLZ_240312,[]
-74,gpt-3.5-turbo-0314,0.0794,mt-bench,BLZ_240312,[]
-75,wizardlm-70b-v1.0,0.0771,mt-bench,BLZ_240312,[]
-76,tulu-2-dpo-70b,0.0789,mt-bench,BLZ_240312,[]
-77,vicuna-33b,0.0712,mt-bench,BLZ_240312,[]
-78,starling-lm-7b-alpha,0.0809,mt-bench,BLZ_240312,[]
-79,deepseek-llm-67b-chat,0.08529999999999999,mt-bench,BLZ_240312,[]
-80,llama-2-70b-chat,0.06860000000000001,mt-bench,BLZ_240312,[]
-81,nv-llama2-70b-steerlm-chat,0.0754,mt-bench,BLZ_240312,[]
-82,openhermes-2.5-mistral-7b,0.07690000000000001,mt-bench,BLZ_240312,[]
-83,openchat-3.5,0.0781,mt-bench,BLZ_240312,[]
-84,pplx-70b-online,0.0588,mt-bench,BLZ_240312,[]
-85,gpt-3.5-turbo-1106,0.0832,mt-bench,BLZ_240312,[]
-86,solar-10.7b-instruct-v1.0,0.0758,mt-bench,BLZ_240312,[]
-88,wizardlm-13b-v1.2,0.07200000000000001,mt-bench,BLZ_240312,[]
-89,zephyr-7b-beta,0.07339999999999999,mt-bench,BLZ_240312,[]
-90,mpt-30b-chat,0.0639,mt-bench,BLZ_240312,[]
-92,llama-2-13b-chat,0.0665,mt-bench,BLZ_240312,[]
-93,vicuna-13b,0.06570000000000001,mt-bench,BLZ_240312,[]
-95,zephyr-7b-alpha,0.0688,mt-bench,BLZ_240312,[]
-96,qwen-14b-chat,0.0696,mt-bench,BLZ_240312,[]
-98,guanaco-33b,0.0653,mt-bench,BLZ_240312,[]
-99,llama-2-7b-chat,0.06269999999999999,mt-bench,BLZ_240312,[]
-101,mistral-7b-instruct-v0.1,0.0684,mt-bench,BLZ_240312,[]
-102,palm-chat-bison-001,0.064,mt-bench,BLZ_240312,[]
-103,vicuna-7b,0.0617,mt-bench,BLZ_240312,[]
-104,koala-13b,0.0535,mt-bench,BLZ_240312,[]
-106,gpt4all-13b-snoozy,0.0541,mt-bench,BLZ_240312,[]
-107,mpt-7b-chat,0.0542,mt-bench,BLZ_240312,[]
-108,chatglm2-6b,0.0496,mt-bench,BLZ_240312,[]
-109,rwkv-4-raven-14b,0.0398,mt-bench,BLZ_240312,[]
-110,alpaca-13b,0.0453,mt-bench,BLZ_240312,[]
-111,openassistant-pythia-12b,0.0432,mt-bench,BLZ_240312,[]
-112,chatglm-6b,0.045,mt-bench,BLZ_240312,[]
-113,fastchat-t5-3b,0.0304,mt-bench,BLZ_240312,[]
-114,stablelm-tuned-alpha-7b,0.0275,mt-bench,BLZ_240312,[]
-115,dolly-v2-12b,0.032799999999999996,mt-bench,BLZ_240312,[]
-116,llama-13b,0.026099999999999998,mt-bench,BLZ_240312,[]
-0,gpt-4-0613,0.957,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-1,llama-3-70b,0.902,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-2,mixtral-8x22b,0.855,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-3,palmyra-x-v3-72b,0.826,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-4,gpt-4-turbo-1106-preview,0.821,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-5,palm-2-unicorn,0.781,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-6,claude-3-opus-20240229,0.762,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-7,qwen1.5-72b,0.757,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-8,palmyra-x-v2-33b,0.736,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-9,yi-34b,0.723,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-10,qwen1.5-32b,0.689,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-11,claude-v1.3,0.689,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-12,mixtral-8x7b-32k-seqlen,0.679,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-13,palm-2-bison,0.655,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-14,claude-2.0,0.651,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-15,deepseek-llm-67b-chat,0.645,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-16,llama-2-70b,0.609,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-17,claude-2.1,0.594,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-18,gpt-3.5-text-davinci-003,0.577,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-19,qwen1.5-14b,0.574,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-20,claude-instant-1.2,0.551,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-21,llama-3-8b,0.519,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-22,gpt-3.5-turbo-0613,0.502,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-23,gemma-7b,0.47,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-24,claude-3-sonnet-20240229,0.468,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-25,gpt-3.5-text-davinci-002,0.468,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-26,llama-65b,0.466,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-27,mistral-large-2402,0.46,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-28,cohere-command,0.421,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-29,dbrx-instructruct,0.419,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-30,mistral-v0.1-7b,0.415,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-31,mistral-small-2402,0.415,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-32,mistral-medium-2312,0.383,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-33,qwen1.5-7b,0.377,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-34,claude-3-haiku-20240307,0.377,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-35,yi-6b,0.351,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-36,llama-2-13b,0.332,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-37,jurassic-2-jumbo-178b,0.317,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-38,falcon-40b,0.306,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-39,phi-2,0.26,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-40,jurassic-2-grande-17b,0.253,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-41,llama-2-7b,0.234,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-42,luminous-supreme-70b,0.213,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-43,cohere-command-light,0.166,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-44,luminous-extended-30b,0.119,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-45,falcon-7b,0.1,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-46,olmo-7b,0.083,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-47,luminous-base-13b,0.072,helm_lite_mwr,helm_lite_240610,"['narrativeqa', 'naturalquestions_open', 'naturalquestions_closed', 'openbookqa', 'mmlu', 'math', 'gsm8k', 'legalbench', 'medqa', 'wmt_2014']"
-0,llama-2-70b,0.944,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-1,llama-65b,0.908,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-2,text-davinci-002,0.905,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-3,mistral-v0.1-7b,0.884,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-4,cohere-command-beta-52.4b,0.874,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-5,text-davinci-003,0.872,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-6,jurassic-2-jumbo-178b,0.824,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-7,llama-2-13b,0.823,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-8,tnlg-v2-530b,0.787,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-9,gpt-3.5-turbo-0613,0.783,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-10,llama-30b,0.781,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-11,anthropic-lm-v4-s3-52b,0.78,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-12,gpt-3.5-turbo-0301,0.76,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-13,jurassic-2-grande-17b,0.743,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-14,palmyra-x-43b,0.732,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-15,falcon-40b,0.729,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-16,falcon-instruct-40b,0.727,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-17,mpt-instruct-30b,0.716,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-18,mpt-30b,0.714,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-19,j1-grande-v2-beta-17b,0.706,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-20,vicuna-v1.3-13b,0.706,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-21,cohere-command-beta-6.1b,0.675,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-22,cohere-xlarge-v20221108-52.4b,0.664,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-23,luminous-supreme-70b,0.662,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-24,vicuna-v1.3-7b,0.625,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-25,opt-175b,0.609,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-26,llama-2-7b,0.607,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-27,llama-13b,0.595,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-28,instructpalmyra-30b,0.568,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-29,cohere-xlarge-v20220609-52.4b,0.56,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-30,jurassic-2-large-7.5b,0.553,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-31,davinci-175b,0.538,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-32,llama-7b,0.533,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-33,redpajama-incite-instruct-7b,0.524,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-34,j1-jumbo-v1-178b,0.517,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-35,glm-130b,0.512,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-36,luminous-extended-30b,0.485,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-37,opt-66b,0.448,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-38,bloom-176b,0.446,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-39,j1-grande-v1-17b,0.433,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-40,alpaca-7b,0.381,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-41,falcon-7b,0.378,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-42,redpajama-incite-base-7b,0.378,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-43,cohere-large-v20220720-13.1b,0.372,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-44,redpajama-incite-instruct-v1-3b,0.366,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-45,text-curie-001,0.36,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-46,gpt-neox-20b,0.351,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-47,luminous-base-13b,0.315,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-48,cohere-medium-v20221108-6.1b,0.312,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-49,redpajama-incite-base-v1-3b,0.311,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-50,tnlg-v2-6.7b,0.309,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-51,j1-large-v1-7.5b,0.285,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-52,gpt-j-6b,0.273,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-53,pythia-12b,0.257,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-54,curie-6.7b,0.247,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-55,falcon-instruct-7b,0.244,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-56,cohere-medium-v20220720-6.1b,0.23,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-57,text-babbage-001,0.229,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-58,t0pp-11b,0.197,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-59,pythia-6.9b,0.196,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-60,ul2-20b,0.167,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-61,t5-11b,0.131,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-62,babbage-1.3b,0.114,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-63,cohere-small-v20220720-410m,0.109,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-64,ada-350m,0.108,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-65,text-ada-001,0.107,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-66,yalm-100b,0.075,helm_mwr,helm_classic_240130,"['mmlu', 'boolq', 'narrativeqa', 'naturalquestions-closed', 'naturalquestions-open', 'quac', 'hellaswag', 'openbookqa', 'truthfulqa', 'ms-marco-regular', 'ms-marco-trec', 'cnn/dailymail', 'xsum', 'imdb', 'civilcomments', 'raft']"
-67,llama-2-70b,0.582,mmlu,helm_classic_240130,[]
-68,llama-65b,0.584,mmlu,helm_classic_240130,[]
-69,text-davinci-002,0.568,mmlu,helm_classic_240130,[]
-70,mistral-v0.1-7b,0.572,mmlu,helm_classic_240130,[]
-71,cohere-command-beta-52.4b,0.452,mmlu,helm_classic_240130,[]
-72,text-davinci-003,0.569,mmlu,helm_classic_240130,[]
-73,jurassic-2-jumbo-178b,0.48,mmlu,helm_classic_240130,[]
-74,llama-2-13b,0.507,mmlu,helm_classic_240130,[]
-75,tnlg-v2-530b,0.469,mmlu,helm_classic_240130,[]
-76,gpt-3.5-turbo-0613,0.391,mmlu,helm_classic_240130,[]
-77,llama-30b,0.531,mmlu,helm_classic_240130,[]
-78,anthropic-lm-v4-s3-52b,0.481,mmlu,helm_classic_240130,[]
-79,gpt-3.5-turbo-0301,0.59,mmlu,helm_classic_240130,[]
-80,jurassic-2-grande-17b,0.475,mmlu,helm_classic_240130,[]
-81,palmyra-x-43b,0.609,mmlu,helm_classic_240130,[]
-82,falcon-40b,0.509,mmlu,helm_classic_240130,[]
-83,falcon-instruct-40b,0.497,mmlu,helm_classic_240130,[]
-84,mpt-instruct-30b,0.444,mmlu,helm_classic_240130,[]
-85,mpt-30b,0.437,mmlu,helm_classic_240130,[]
-86,j1-grande-v2-beta-17b,0.445,mmlu,helm_classic_240130,[]
-87,vicuna-v1.3-13b,0.462,mmlu,helm_classic_240130,[]
-88,cohere-command-beta-6.1b,0.406,mmlu,helm_classic_240130,[]
-89,cohere-xlarge-v20221108-52.4b,0.382,mmlu,helm_classic_240130,[]
-90,luminous-supreme-70b,0.38,mmlu,helm_classic_240130,[]
-91,vicuna-v1.3-7b,0.434,mmlu,helm_classic_240130,[]
-92,opt-175b,0.318,mmlu,helm_classic_240130,[]
-93,llama-2-7b,0.431,mmlu,helm_classic_240130,[]
-94,llama-13b,0.422,mmlu,helm_classic_240130,[]
-95,instructpalmyra-30b,0.403,mmlu,helm_classic_240130,[]
-96,cohere-xlarge-v20220609-52.4b,0.353,mmlu,helm_classic_240130,[]
-97,jurassic-2-large-7.5b,0.339,mmlu,helm_classic_240130,[]
-98,davinci-175b,0.422,mmlu,helm_classic_240130,[]
-99,llama-7b,0.321,mmlu,helm_classic_240130,[]
-100,redpajama-incite-instruct-7b,0.363,mmlu,helm_classic_240130,[]
-101,j1-jumbo-v1-178b,0.259,mmlu,helm_classic_240130,[]
-102,glm-130b,0.344,mmlu,helm_classic_240130,[]
-103,luminous-extended-30b,0.321,mmlu,helm_classic_240130,[]
-104,opt-66b,0.276,mmlu,helm_classic_240130,[]
-105,bloom-176b,0.299,mmlu,helm_classic_240130,[]
-106,j1-grande-v1-17b,0.27,mmlu,helm_classic_240130,[]
-107,alpaca-7b,0.385,mmlu,helm_classic_240130,[]
-108,falcon-7b,0.286,mmlu,helm_classic_240130,[]
-109,redpajama-incite-base-7b,0.302,mmlu,helm_classic_240130,[]
-110,cohere-large-v20220720-13.1b,0.324,mmlu,helm_classic_240130,[]
-111,redpajama-incite-instruct-v1-3b,0.257,mmlu,helm_classic_240130,[]
-112,text-curie-001,0.237,mmlu,helm_classic_240130,[]
-113,gpt-neox-20b,0.276,mmlu,helm_classic_240130,[]
-114,luminous-base-13b,0.27,mmlu,helm_classic_240130,[]
-115,cohere-medium-v20221108-6.1b,0.254,mmlu,helm_classic_240130,[]
-116,redpajama-incite-base-v1-3b,0.263,mmlu,helm_classic_240130,[]
-117,tnlg-v2-6.7b,0.242,mmlu,helm_classic_240130,[]
-118,j1-large-v1-7.5b,0.241,mmlu,helm_classic_240130,[]
-119,gpt-j-6b,0.249,mmlu,helm_classic_240130,[]
-120,pythia-12b,0.274,mmlu,helm_classic_240130,[]
-121,curie-6.7b,0.243,mmlu,helm_classic_240130,[]
-122,falcon-instruct-7b,0.275,mmlu,helm_classic_240130,[]
-123,cohere-medium-v20220720-6.1b,0.279,mmlu,helm_classic_240130,[]
-124,text-babbage-001,0.229,mmlu,helm_classic_240130,[]
-125,t0pp-11b,0.407,mmlu,helm_classic_240130,[]
-126,pythia-6.9b,0.236,mmlu,helm_classic_240130,[]
-127,ul2-20b,0.291,mmlu,helm_classic_240130,[]
-128,t5-11b,0.29,mmlu,helm_classic_240130,[]
-129,babbage-1.3b,0.235,mmlu,helm_classic_240130,[]
-130,cohere-small-v20220720-410m,0.264,mmlu,helm_classic_240130,[]
-131,ada-350m,0.243,mmlu,helm_classic_240130,[]
-132,text-ada-001,0.238,mmlu,helm_classic_240130,[]
-133,yalm-100b,0.243,mmlu,helm_classic_240130,[]
-0,gpt-4o-0513,35.7,wildbench-mix,wildbench_240612,[]
-1,gpt-4-turbo-0409,34.6,wildbench-mix,wildbench_240612,[]
-2,gpt-4-turbo-0125,29.9,wildbench-mix,wildbench_240612,[]
-3,gemini-1.5-pro,27.8,wildbench-mix,wildbench_240612,[]
-4,llama-3-70b-inst,21.0,wildbench-mix,wildbench_240612,[]
-5,claude-3-opus,20.1,wildbench-mix,wildbench_240612,[]
-6,gemini-1.5-flash,17.4,wildbench-mix,wildbench_240612,[]
-7,yi-1.5-34b-chat,16.8,wildbench-mix,wildbench_240612,[]
-8,llama3-inst-8b-simpo,14.0,wildbench-mix,wildbench_240612,[]
-9,claude-3-sonnet,7.2,wildbench-mix,wildbench_240612,[]
-10,qwen1.5-72b-chat,4.4,wildbench-mix,wildbench_240612,[]
-11,command-r-plus,0.4,wildbench-mix,wildbench_240612,[]
-12,claude-3-haiku,-8.5,wildbench-mix,wildbench_240612,[]
-13,mistral-large,-10.5,wildbench-mix,wildbench_240612,[]
-14,starlinglm-7b-beta,-11.9,wildbench-mix,wildbench_240612,[]
-15,llama-3-8b-inst,-14.6,wildbench-mix,wildbench_240612,[]
-16,command-r,-16.0,wildbench-mix,wildbench_240612,[]
-17,mixtral-8x7b-inst,-18.8,wildbench-mix,wildbench_240612,[]
-18,dbrx-instruct,-21.6,wildbench-mix,wildbench_240612,[]
-19,yi-1.5-6b-chat,-24.3,wildbench-mix,wildbench_240612,[]
-20,mistral-7b-inst-v0.2,-25.0,wildbench-mix,wildbench_240612,[]
-21,tulu-2-dpo-70b,-25.4,wildbench-mix,wildbench_240612,[]
-22,llama-2-70b-chat,-26.8,wildbench-mix,wildbench_240612,[]
-23,qwen1.5-7b-chat,-27.0,wildbench-mix,wildbench_240612,[]
-24,phi-3-medium-128k,-33.3,wildbench-mix,wildbench_240612,[]
-25,gpt-3.5-turbo-0125,-33.5,wildbench-mix,wildbench_240612,[]
-26,llama-2-7b-chat,-48.0,wildbench-mix,wildbench_240612,[]
-27,gemma-7b-it,-57.0,wildbench-mix,wildbench_240612,[]
-28,gemma-2b-it,-74.1,wildbench-mix,wildbench_240612,[]
-13,flan-t5-xxl,0.2244897959183673,mmlu_pro,bluebench_v02,[]
-30,granite-13b-chat-v2,0.2857142857142857,mmlu_pro,bluebench_v02,[]
-41,granite-13b-instruct-v2,0.0408163265306122,mmlu_pro,bluebench_v02,[]
-50,granite-7b-lab,0.2423469387755102,mmlu_pro,bluebench_v02,[]
-60,llama-2-13b-chat,0.0943877551020408,mmlu_pro,bluebench_v02,[]
-70,llama-2-70b,0.4081632653061224,mmlu_pro,bluebench_v02,[]
-81,llama-3-70b-instruct,0.4285714285714285,mmlu_pro,bluebench_v02,[]
-92,llama-3-8b,0.375,mmlu_pro,bluebench_v02,[]
-103,llama-3-8b-instruct,0.0994897959183673,mmlu_pro,bluebench_v02,[]
-112,llama-30b,0.3061224489795918,mmlu_pro,bluebench_v02,[]
-121,llama-7b,0.1326530612244897,mmlu_pro,bluebench_v02,[]
-132,mistral-v0.1-7b,0.2857142857142857,mmlu_pro,bluebench_v02,[]
-143,mixtral-8x7b-instruct-v01,0.375,mmlu_pro,bluebench_v02,[]
-153,vicuna-13b-v1.5-16k,0.2857142857142857,mmlu_pro,bluebench_v02,[]
-162,vicuna-33b-v1.3,0.2653061224489796,mmlu_pro,bluebench_v02,[]
-172,vicuna-v1.3-7b,0.1938775510204081,mmlu_pro,bluebench_v02,[]
-182,vicuna-7b-v1.5,0.2857142857142857,mmlu_pro,bluebench_v02,[]
-192,zephyr-7b-beta,0.2959183673469387,mmlu_pro,bluebench_v02,[]

assets/livebench.csv

@@ -1,365 +0,0 @@
-,model,scenario,score,aggragated_from,source
-0,claude_3_5_sonnet_20240620,livebench_lb,61.16,[],livebench_240701
-1,gpt_4o_2024_05_13,livebench_lb,54.96,[],livebench_240701
-2,gpt_4_turbo_2024_04_09,livebench_lb,53.0,[],livebench_240701
-3,gpt_4_1106_preview,livebench_lb,52.17,[],livebench_240701
-4,claude_3_opus_20240229,livebench_lb,50.75,[],livebench_240701
-5,gpt_4_0125_preview,livebench_lb,49.39,[],livebench_240701
-6,deepseek_coder_v2,livebench_lb,46.79,[],livebench_240701
-7,gemini_1.5_pro_api_0514,livebench_lb,44.35,[],livebench_240701
-8,gemma_2_27b_it,livebench_lb,41.22,[],livebench_240701
-9,gemini_1.5_flash_api_0514,livebench_lb,40.89,[],livebench_240701
-10,qwen2_72b_instruct,livebench_lb,40.16,[],livebench_240701
-11,acm_rewrite_qwen2_72b_chat,livebench_lb,39.6,[],livebench_240701
-12,mistral_large_2402,livebench_lb,38.92,[],livebench_240701
-13,deepseek_chat_v2,livebench_lb,38.39,[],livebench_240701
-14,claude_3_sonnet_20240229,livebench_lb,38.08,[],livebench_240701
-15,meta_llama_3_70b_instruct,livebench_lb,37.38,[],livebench_240701
-16,claude_3_haiku_20240307,livebench_lb,35.32,[],livebench_240701
-17,mixtral_8x22b_instruct_v0.1,livebench_lb,34.84,[],livebench_240701
-18,gpt_3.5_turbo_0125,livebench_lb,34.43,[],livebench_240701
-19,gpt_3.5_turbo_1106,livebench_lb,34.14,[],livebench_240701
-20,command_r_plus,livebench_lb,32.86,[],livebench_240701
-21,mistral_small_2402,livebench_lb,32.8,[],livebench_240701
-22,gemma_2_9b_it,livebench_lb,31.57,[],livebench_240701
-23,phi_3_medium_4k_instruct,livebench_lb,30.33,[],livebench_240701
-24,phi_3_medium_128k_instruct,livebench_lb,29.64,[],livebench_240701
-25,deepseek_coder_v2_lite_instruct,livebench_lb,29.15,[],livebench_240701
-26,qwen1.5_110b_chat,livebench_lb,28.96,[],livebench_240701
-27,qwen1.5_72b_chat,livebench_lb,28.89,[],livebench_240701
-28,command_r,livebench_lb,27.23,[],livebench_240701
-29,phi_3_small_128k_instruct,livebench_lb,27.19,[],livebench_240701
-30,meta_llama_3_8b_instruct,livebench_lb,26.67,[],livebench_240701
-31,qwen2_7b_instruct,livebench_lb,26.45,[],livebench_240701
-32,phi_3_small_8k_instruct,livebench_lb,26.24,[],livebench_240701
-33,openhermes_2.5_mistral_7b,livebench_lb,23.3,[],livebench_240701
-34,mixtral_8x7b_instruct_v0.1,livebench_lb,22.5,[],livebench_240701
-35,mistral_7b_instruct_v0.2,livebench_lb,19.33,[],livebench_240701
-36,phi_3_mini_4k_instruct,livebench_lb,19.27,[],livebench_240701
-37,zephyr_7b_alpha,livebench_lb,19.22,[],livebench_240701
-38,phi_3_mini_128k_instruct,livebench_lb,18.04,[],livebench_240701
-39,zephyr_7b_beta,livebench_lb,17.32,[],livebench_240701
-40,deepseek_v2_lite_chat,livebench_lb,17.14,[],livebench_240701
-41,qwen1.5_7b_chat,livebench_lb,16.5,[],livebench_240701
-42,starling_lm_7b_beta,livebench_lb,16.44,[],livebench_240701
-43,vicuna_7b_v1.5_16k,livebench_lb,13.71,[],livebench_240701
-44,vicuna_7b_v1.5,livebench_lb,11.73,[],livebench_240701
-45,qwen1.5_4b_chat,livebench_lb,11.13,[],livebench_240701
-46,llama_2_7b_chat,livebench_lb,10.25,[],livebench_240701
-47,qwen2_1.5b_instruct,livebench_lb,9.96,[],livebench_240701
-48,yi_6b_chat,livebench_lb,8.79,[],livebench_240701
-49,qwen2_0.5b_instruct,livebench_lb,6.78,[],livebench_240701
-50,qwen1.5_1.8b_chat,livebench_lb,6.09,[],livebench_240701
-51,qwen1.5_0.5b_chat,livebench_lb,5.26,[],livebench_240701
-52,claude_3_5_sonnet_20240620,reasoning_lb,64.0,[],livebench_240701
-53,gpt_4o_2024_05_13,reasoning_lb,55.0,[],livebench_240701
-54,gpt_4_turbo_2024_04_09,reasoning_lb,54.0,[],livebench_240701
-55,gpt_4_1106_preview,reasoning_lb,52.0,[],livebench_240701
-56,claude_3_opus_20240229,reasoning_lb,41.0,[],livebench_240701
-57,gpt_4_0125_preview,reasoning_lb,48.0,[],livebench_240701
-58,deepseek_coder_v2,reasoning_lb,49.0,[],livebench_240701
-59,gemini_1.5_pro_api_0514,reasoning_lb,33.0,[],livebench_240701
-60,gemma_2_27b_it,reasoning_lb,31.0,[],livebench_240701
-61,gemini_1.5_flash_api_0514,reasoning_lb,30.0,[],livebench_240701
-62,qwen2_72b_instruct,reasoning_lb,42.0,[],livebench_240701
-63,acm_rewrite_qwen2_72b_chat,reasoning_lb,37.0,[],livebench_240701
-64,mistral_large_2402,reasoning_lb,35.0,[],livebench_240701
-65,deepseek_chat_v2,reasoning_lb,29.0,[],livebench_240701
-66,claude_3_sonnet_20240229,reasoning_lb,26.0,[],livebench_240701
-67,meta_llama_3_70b_instruct,reasoning_lb,31.0,[],livebench_240701
-68,claude_3_haiku_20240307,reasoning_lb,26.0,[],livebench_240701
-69,mixtral_8x22b_instruct_v0.1,reasoning_lb,29.0,[],livebench_240701
-70,gpt_3.5_turbo_0125,reasoning_lb,26.0,[],livebench_240701
-71,gpt_3.5_turbo_1106,reasoning_lb,28.0,[],livebench_240701
-72,command_r_plus,reasoning_lb,32.0,[],livebench_240701
-73,mistral_small_2402,reasoning_lb,28.0,[],livebench_240701
-74,gemma_2_9b_it,reasoning_lb,19.0,[],livebench_240701
-75,phi_3_medium_4k_instruct,reasoning_lb,35.0,[],livebench_240701
-76,phi_3_medium_128k_instruct,reasoning_lb,31.0,[],livebench_240701
-77,deepseek_coder_v2_lite_instruct,reasoning_lb,22.0,[],livebench_240701
-78,qwen1.5_110b_chat,reasoning_lb,26.0,[],livebench_240701
-79,qwen1.5_72b_chat,reasoning_lb,21.0,[],livebench_240701
-80,command_r,reasoning_lb,28.0,[],livebench_240701
-81,phi_3_small_128k_instruct,reasoning_lb,36.0,[],livebench_240701
-82,meta_llama_3_8b_instruct,reasoning_lb,25.0,[],livebench_240701
-83,qwen2_7b_instruct,reasoning_lb,20.0,[],livebench_240701
-84,phi_3_small_8k_instruct,reasoning_lb,23.0,[],livebench_240701
-85,openhermes_2.5_mistral_7b,reasoning_lb,17.0,[],livebench_240701
-86,mixtral_8x7b_instruct_v0.1,reasoning_lb,18.0,[],livebench_240701
-87,mistral_7b_instruct_v0.2,reasoning_lb,13.0,[],livebench_240701
-88,phi_3_mini_4k_instruct,reasoning_lb,19.0,[],livebench_240701
-89,zephyr_7b_alpha,reasoning_lb,17.0,[],livebench_240701
-90,phi_3_mini_128k_instruct,reasoning_lb,10.0,[],livebench_240701
-91,zephyr_7b_beta,reasoning_lb,16.0,[],livebench_240701
-92,deepseek_v2_lite_chat,reasoning_lb,13.0,[],livebench_240701
-93,qwen1.5_7b_chat,reasoning_lb,13.0,[],livebench_240701
-94,starling_lm_7b_beta,reasoning_lb,19.0,[],livebench_240701
-95,vicuna_7b_v1.5_16k,reasoning_lb,15.0,[],livebench_240701
-96,vicuna_7b_v1.5,reasoning_lb,12.0,[],livebench_240701
-97,qwen1.5_4b_chat,reasoning_lb,13.0,[],livebench_240701
-98,llama_2_7b_chat,reasoning_lb,5.0,[],livebench_240701
-99,qwen2_1.5b_instruct,reasoning_lb,8.0,[],livebench_240701
-100,yi_6b_chat,reasoning_lb,8.0,[],livebench_240701
-101,qwen2_0.5b_instruct,reasoning_lb,3.0,[],livebench_240701
-102,qwen1.5_1.8b_chat,reasoning_lb,5.0,[],livebench_240701
-103,qwen1.5_0.5b_chat,reasoning_lb,4.0,[],livebench_240701
-104,claude_3_5_sonnet_20240620,coding_lb,63.21,[],livebench_240701
-105,gpt_4o_2024_05_13,coding_lb,46.37,[],livebench_240701
-106,gpt_4_turbo_2024_04_09,coding_lb,47.05,[],livebench_240701
-107,gpt_4_1106_preview,coding_lb,44.37,[],livebench_240701
-108,claude_3_opus_20240229,coding_lb,40.05,[],livebench_240701
-109,gpt_4_0125_preview,coding_lb,44.05,[],livebench_240701
-110,deepseek_coder_v2,coding_lb,41.05,[],livebench_240701
-111,gemini_1.5_pro_api_0514,coding_lb,32.79,[],livebench_240701
-112,gemma_2_27b_it,coding_lb,36.74,[],livebench_240701
-113,gemini_1.5_flash_api_0514,coding_lb,39.05,[],livebench_240701
-114,qwen2_72b_instruct,coding_lb,31.79,[],livebench_240701
-115,acm_rewrite_qwen2_72b_chat,coding_lb,39.05,[],livebench_240701
-116,mistral_large_2402,coding_lb,26.84,[],livebench_240701
-117,deepseek_chat_v2,coding_lb,33.47,[],livebench_240701
-118,claude_3_sonnet_20240229,coding_lb,25.21,[],livebench_240701
-119,meta_llama_3_70b_instruct,coding_lb,20.95,[],livebench_240701
-120,claude_3_haiku_20240307,coding_lb,24.53,[],livebench_240701
-121,mixtral_8x22b_instruct_v0.1,coding_lb,33.11,[],livebench_240701
-122,gpt_3.5_turbo_0125,coding_lb,29.16,[],livebench_240701
-123,gpt_3.5_turbo_1106,coding_lb,26.84,[],livebench_240701
-124,command_r_plus,coding_lb,20.26,[],livebench_240701
-125,mistral_small_2402,coding_lb,24.21,[],livebench_240701
-126,gemma_2_9b_it,coding_lb,22.21,[],livebench_240701
-127,phi_3_medium_4k_instruct,coding_lb,20.58,[],livebench_240701
-128,phi_3_medium_128k_instruct,coding_lb,21.58,[],livebench_240701
-129,deepseek_coder_v2_lite_instruct,coding_lb,26.84,[],livebench_240701
-130,qwen1.5_110b_chat,coding_lb,22.21,[],livebench_240701
-131,qwen1.5_72b_chat,coding_lb,22.89,[],livebench_240701
-132,command_r,coding_lb,14.95,[],livebench_240701
-133,phi_3_small_128k_instruct,coding_lb,25.84,[],livebench_240701
-134,meta_llama_3_8b_instruct,coding_lb,18.26,[],livebench_240701
-135,qwen2_7b_instruct,coding_lb,29.21,[],livebench_240701
-136,phi_3_small_8k_instruct,coding_lb,19.58,[],livebench_240701
-137,openhermes_2.5_mistral_7b,coding_lb,11.63,[],livebench_240701
-138,mixtral_8x7b_instruct_v0.1,coding_lb,11.32,[],livebench_240701
-139,mistral_7b_instruct_v0.2,coding_lb,11.63,[],livebench_240701
-140,phi_3_mini_4k_instruct,coding_lb,14.95,[],livebench_240701
-141,zephyr_7b_alpha,coding_lb,11.32,[],livebench_240701
-142,phi_3_mini_128k_instruct,coding_lb,11.63,[],livebench_240701
-143,zephyr_7b_beta,coding_lb,8.32,[],livebench_240701
-144,deepseek_v2_lite_chat,coding_lb,8.63,[],livebench_240701
-145,qwen1.5_7b_chat,coding_lb,6.63,[],livebench_240701
-146,starling_lm_7b_beta,coding_lb,18.26,[],livebench_240701
-147,vicuna_7b_v1.5_16k,coding_lb,1.32,[],livebench_240701
-148,vicuna_7b_v1.5,coding_lb,1.0,[],livebench_240701
-149,qwen1.5_4b_chat,coding_lb,4.0,[],livebench_240701
-150,llama_2_7b_chat,coding_lb,0.0,[],livebench_240701
-151,qwen2_1.5b_instruct,coding_lb,5.63,[],livebench_240701
-152,yi_6b_chat,coding_lb,1.32,[],livebench_240701
-153,qwen2_0.5b_instruct,coding_lb,2.0,[],livebench_240701
-154,qwen1.5_1.8b_chat,coding_lb,0.0,[],livebench_240701
-155,qwen1.5_0.5b_chat,coding_lb,0.0,[],livebench_240701
-156,claude_3_5_sonnet_20240620,mathematics_lb,53.75,[],livebench_240701
-157,gpt_4o_2024_05_13,mathematics_lb,49.88,[],livebench_240701
-158,gpt_4_turbo_2024_04_09,mathematics_lb,48.99,[],livebench_240701
-159,gpt_4_1106_preview,mathematics_lb,47.55,[],livebench_240701
-160,claude_3_opus_20240229,mathematics_lb,46.54,[],livebench_240701
-161,gpt_4_0125_preview,mathematics_lb,42.75,[],livebench_240701
-162,deepseek_coder_v2,mathematics_lb,52.19,[],livebench_240701
-163,gemini_1.5_pro_api_0514,mathematics_lb,42.07,[],livebench_240701
-164,gemma_2_27b_it,mathematics_lb,36.23,[],livebench_240701
-165,gemini_1.5_flash_api_0514,mathematics_lb,38.54,[],livebench_240701
-166,qwen2_72b_instruct,mathematics_lb,43.44,[],livebench_240701
-167,acm_rewrite_qwen2_72b_chat,mathematics_lb,40.32,[],livebench_240701
-168,mistral_large_2402,mathematics_lb,32.2,[],livebench_240701
-169,deepseek_chat_v2,mathematics_lb,33.23,[],livebench_240701
-170,claude_3_sonnet_20240229,mathematics_lb,29.65,[],livebench_240701
-171,meta_llama_3_70b_instruct,mathematics_lb,32.31,[],livebench_240701
-172,claude_3_haiku_20240307,mathematics_lb,25.72,[],livebench_240701
-173,mixtral_8x22b_instruct_v0.1,mathematics_lb,26.94,[],livebench_240701
-174,gpt_3.5_turbo_0125,mathematics_lb,25.54,[],livebench_240701
-175,gpt_3.5_turbo_1106,mathematics_lb,28.13,[],livebench_240701
-176,command_r_plus,mathematics_lb,24.85,[],livebench_240701
-177,mistral_small_2402,mathematics_lb,26.76,[],livebench_240701
-178,gemma_2_9b_it,mathematics_lb,23.98,[],livebench_240701
-179,phi_3_medium_4k_instruct,mathematics_lb,27.54,[],livebench_240701
-180,phi_3_medium_128k_instruct,mathematics_lb,24.25,[],livebench_240701
-181,deepseek_coder_v2_lite_instruct,mathematics_lb,34.09,[],livebench_240701
-182,qwen1.5_110b_chat,mathematics_lb,25.58,[],livebench_240701
-183,qwen1.5_72b_chat,mathematics_lb,26.82,[],livebench_240701
-184,command_r,mathematics_lb,16.92,[],livebench_240701
-185,phi_3_small_128k_instruct,mathematics_lb,24.84,[],livebench_240701
-186,meta_llama_3_8b_instruct,mathematics_lb,17.58,[],livebench_240701
-187,qwen2_7b_instruct,mathematics_lb,25.83,[],livebench_240701
-188,phi_3_small_8k_instruct,mathematics_lb,24.15,[],livebench_240701
-189,openhermes_2.5_mistral_7b,mathematics_lb,20.1,[],livebench_240701
-190,mixtral_8x7b_instruct_v0.1,mathematics_lb,18.97,[],livebench_240701
-191,mistral_7b_instruct_v0.2,mathematics_lb,16.04,[],livebench_240701
-192,phi_3_mini_4k_instruct,mathematics_lb,19.88,[],livebench_240701
-193,zephyr_7b_alpha,mathematics_lb,9.61,[],livebench_240701
-194,phi_3_mini_128k_instruct,mathematics_lb,21.48,[],livebench_240701
-195,zephyr_7b_beta,mathematics_lb,11.23,[],livebench_240701
-196,deepseek_v2_lite_chat,mathematics_lb,11.99,[],livebench_240701
-197,qwen1.5_7b_chat,mathematics_lb,12.86,[],livebench_240701
-198,starling_lm_7b_beta,mathematics_lb,13.82,[],livebench_240701
-199,vicuna_7b_v1.5_16k,mathematics_lb,6.61,[],livebench_240701
-200,vicuna_7b_v1.5,mathematics_lb,4.33,[],livebench_240701
-201,qwen1.5_4b_chat,mathematics_lb,7.08,[],livebench_240701
-202,llama_2_7b_chat,mathematics_lb,4.78,[],livebench_240701
-203,qwen2_1.5b_instruct,mathematics_lb,7.16,[],livebench_240701
-204,yi_6b_chat,mathematics_lb,7.14,[],livebench_240701
-205,qwen2_0.5b_instruct,mathematics_lb,4.22,[],livebench_240701
-206,qwen1.5_1.8b_chat,mathematics_lb,2.14,[],livebench_240701
-207,qwen1.5_0.5b_chat,mathematics_lb,3.39,[],livebench_240701
-208,claude_3_5_sonnet_20240620,data_analysis_lb,56.74,[],livebench_240701
-209,gpt_4o_2024_05_13,data_analysis_lb,52.41,[],livebench_240701
-210,gpt_4_turbo_2024_04_09,data_analysis_lb,51.32,[],livebench_240701
-211,gpt_4_1106_preview,data_analysis_lb,51.33,[],livebench_240701
-212,claude_3_opus_20240229,data_analysis_lb,54.32,[],livebench_240701
-213,gpt_4_0125_preview,data_analysis_lb,54.06,[],livebench_240701
-214,deepseek_coder_v2,data_analysis_lb,38.25,[],livebench_240701
-215,gemini_1.5_pro_api_0514,data_analysis_lb,52.81,[],livebench_240701
-216,gemma_2_27b_it,data_analysis_lb,43.58,[],livebench_240701
-217,gemini_1.5_flash_api_0514,data_analysis_lb,44.03,[],livebench_240701
-218,qwen2_72b_instruct,data_analysis_lb,26.24,[],livebench_240701
-219,acm_rewrite_qwen2_72b_chat,data_analysis_lb,26.19,[],livebench_240701
-220,mistral_large_2402,data_analysis_lb,42.55,[],livebench_240701
-221,deepseek_chat_v2,data_analysis_lb,38.03,[],livebench_240701
-222,claude_3_sonnet_20240229,data_analysis_lb,44.56,[],livebench_240701
-223,meta_llama_3_70b_instruct,data_analysis_lb,42.41,[],livebench_240701
-224,claude_3_haiku_20240307,data_analysis_lb,41.54,[],livebench_240701
-225,mixtral_8x22b_instruct_v0.1,data_analysis_lb,30.33,[],livebench_240701
-226,gpt_3.5_turbo_0125,data_analysis_lb,41.21,[],livebench_240701
-227,gpt_3.5_turbo_1106,data_analysis_lb,41.7,[],livebench_240701
-228,command_r_plus,data_analysis_lb,24.6,[],livebench_240701
-229,mistral_small_2402,data_analysis_lb,31.88,[],livebench_240701
-230,gemma_2_9b_it,data_analysis_lb,35.06,[],livebench_240701
-231,phi_3_medium_4k_instruct,data_analysis_lb,31.63,[],livebench_240701
-232,phi_3_medium_128k_instruct,data_analysis_lb,32.12,[],livebench_240701
-233,deepseek_coder_v2_lite_instruct,data_analysis_lb,33.0,[],livebench_240701
-234,qwen1.5_110b_chat,data_analysis_lb,31.45,[],livebench_240701
-235,qwen1.5_72b_chat,data_analysis_lb,32.98,[],livebench_240701
-236,command_r,data_analysis_lb,31.69,[],livebench_240701
-237,phi_3_small_128k_instruct,data_analysis_lb,27.33,[],livebench_240701
-238,meta_llama_3_8b_instruct,data_analysis_lb,23.33,[],livebench_240701
-239,qwen2_7b_instruct,data_analysis_lb,28.75,[],livebench_240701
-240,phi_3_small_8k_instruct,data_analysis_lb,27.5,[],livebench_240701
-241,openhermes_2.5_mistral_7b,data_analysis_lb,26.92,[],livebench_240701
-242,mixtral_8x7b_instruct_v0.1,data_analysis_lb,28.13,[],livebench_240701
-243,mistral_7b_instruct_v0.2,data_analysis_lb,14.62,[],livebench_240701
-244,phi_3_mini_4k_instruct,data_analysis_lb,14.67,[],livebench_240701
-245,zephyr_7b_alpha,data_analysis_lb,17.4,[],livebench_240701
-246,phi_3_mini_128k_instruct,data_analysis_lb,8.69,[],livebench_240701
-247,zephyr_7b_beta,data_analysis_lb,15.75,[],livebench_240701
-248,deepseek_v2_lite_chat,data_analysis_lb,18.19,[],livebench_240701
-249,qwen1.5_7b_chat,data_analysis_lb,16.23,[],livebench_240701
-250,starling_lm_7b_beta,data_analysis_lb,2.0,[],livebench_240701
-251,vicuna_7b_v1.5_16k,data_analysis_lb,9.27,[],livebench_240701
-252,vicuna_7b_v1.5,data_analysis_lb,2.67,[],livebench_240701
-253,qwen1.5_4b_chat,data_analysis_lb,9.13,[],livebench_240701
-254,llama_2_7b_chat,data_analysis_lb,0.0,[],livebench_240701
-255,qwen2_1.5b_instruct,data_analysis_lb,10.01,[],livebench_240701
-256,yi_6b_chat,data_analysis_lb,4.38,[],livebench_240701
-257,qwen2_0.5b_instruct,data_analysis_lb,2.0,[],livebench_240701
-258,qwen1.5_1.8b_chat,data_analysis_lb,3.33,[],livebench_240701
-259,qwen1.5_0.5b_chat,data_analysis_lb,0.0,[],livebench_240701
-260,claude_3_5_sonnet_20240620,language_lb,56.94,[],livebench_240701
-261,gpt_4o_2024_05_13,language_lb,53.94,[],livebench_240701
-262,gpt_4_turbo_2024_04_09,language_lb,45.26,[],livebench_240701
-263,gpt_4_1106_preview,language_lb,48.37,[],livebench_240701
-264,claude_3_opus_20240229,language_lb,51.72,[],livebench_240701
-265,gpt_4_0125_preview,language_lb,43.55,[],livebench_240701
-266,deepseek_coder_v2,language_lb,33.04,[],livebench_240701
-267,gemini_1.5_pro_api_0514,language_lb,38.25,[],livebench_240701
-268,gemma_2_27b_it,language_lb,32.4,[],livebench_240701
-269,gemini_1.5_flash_api_0514,language_lb,30.69,[],livebench_240701
-270,qwen2_72b_instruct,language_lb,29.21,[],livebench_240701
-271,acm_rewrite_qwen2_72b_chat,language_lb,30.03,[],livebench_240701
-272,mistral_large_2402,language_lb,28.74,[],livebench_240701
-273,deepseek_chat_v2,language_lb,32.29,[],livebench_240701
-274,claude_3_sonnet_20240229,language_lb,38.08,[],livebench_240701
-275,meta_llama_3_70b_instruct,language_lb,34.11,[],livebench_240701
-276,claude_3_haiku_20240307,language_lb,30.07,[],livebench_240701
-277,mixtral_8x22b_instruct_v0.1,language_lb,26.48,[],livebench_240701
-278,gpt_3.5_turbo_0125,language_lb,24.22,[],livebench_240701
-279,gpt_3.5_turbo_1106,language_lb,28.63,[],livebench_240701
-280,command_r_plus,language_lb,23.92,[],livebench_240701
-281,mistral_small_2402,language_lb,22.06,[],livebench_240701
-282,gemma_2_9b_it,language_lb,27.64,[],livebench_240701
-283,phi_3_medium_4k_instruct,language_lb,13.91,[],livebench_240701
-284,phi_3_medium_128k_instruct,language_lb,12.76,[],livebench_240701
-285,deepseek_coder_v2_lite_instruct,language_lb,10.64,[],livebench_240701
-286,qwen1.5_110b_chat,language_lb,13.22,[],livebench_240701
-287,qwen1.5_72b_chat,language_lb,11.37,[],livebench_240701
-288,command_r,language_lb,14.64,[],livebench_240701
-289,phi_3_small_128k_instruct,language_lb,12.28,[],livebench_240701
-290,meta_llama_3_8b_instruct,language_lb,18.72,[],livebench_240701
-291,qwen2_7b_instruct,language_lb,10.21,[],livebench_240701
-292,phi_3_small_8k_instruct,language_lb,14.96,[],livebench_240701
-293,openhermes_2.5_mistral_7b,language_lb,11.37,[],livebench_240701
-294,mixtral_8x7b_instruct_v0.1,language_lb,13.76,[],livebench_240701
-295,mistral_7b_instruct_v0.2,language_lb,9.05,[],livebench_240701
-296,phi_3_mini_4k_instruct,language_lb,7.1,[],livebench_240701
-297,zephyr_7b_alpha,language_lb,7.2,[],livebench_240701
-298,phi_3_mini_128k_instruct,language_lb,6.8,[],livebench_240701
-299,zephyr_7b_beta,language_lb,4.28,[],livebench_240701
-300,deepseek_v2_lite_chat,language_lb,9.2,[],livebench_240701
-301,qwen1.5_7b_chat,language_lb,6.18,[],livebench_240701
-302,starling_lm_7b_beta,language_lb,7.26,[],livebench_240701
-303,vicuna_7b_v1.5_16k,language_lb,7.92,[],livebench_240701
-304,vicuna_7b_v1.5,language_lb,8.66,[],livebench_240701
-305,qwen1.5_4b_chat,language_lb,5.8,[],livebench_240701
-306,llama_2_7b_chat,language_lb,6.86,[],livebench_240701
-307,qwen2_1.5b_instruct,language_lb,3.05,[],livebench_240701
-308,yi_6b_chat,language_lb,4.69,[],livebench_240701
-309,qwen2_0.5b_instruct,language_lb,2.8,[],livebench_240701
-310,qwen1.5_1.8b_chat,language_lb,3.16,[],livebench_240701
-311,qwen1.5_0.5b_chat,language_lb,2.88,[],livebench_240701
-312,claude_3_5_sonnet_20240620,if_lb,72.3,[],livebench_240701
-313,gpt_4o_2024_05_13,if_lb,72.17,[],livebench_240701
-314,gpt_4_turbo_2024_04_09,if_lb,71.39,[],livebench_240701
-315,gpt_4_1106_preview,if_lb,69.39,[],livebench_240701
-316,claude_3_opus_20240229,if_lb,70.87,[],livebench_240701
-317,gpt_4_0125_preview,if_lb,63.92,[],livebench_240701
-318,deepseek_coder_v2,if_lb,67.18,[],livebench_240701
-319,gemini_1.5_pro_api_0514,if_lb,67.2,[],livebench_240701
-320,gemma_2_27b_it,if_lb,67.37,[],livebench_240701
-321,gemini_1.5_flash_api_0514,if_lb,63.01,[],livebench_240701
-322,qwen2_72b_instruct,if_lb,68.27,[],livebench_240701
-323,acm_rewrite_qwen2_72b_chat,if_lb,65.0,[],livebench_240701
-324,mistral_large_2402,if_lb,68.19,[],livebench_240701
-325,deepseek_chat_v2,if_lb,64.34,[],livebench_240701
-326,claude_3_sonnet_20240229,if_lb,65.0,[],livebench_240701
-327,meta_llama_3_70b_instruct,if_lb,63.5,[],livebench_240701
-328,claude_3_haiku_20240307,if_lb,64.03,[],livebench_240701
-329,mixtral_8x22b_instruct_v0.1,if_lb,63.17,[],livebench_240701
-330,gpt_3.5_turbo_0125,if_lb,60.47,[],livebench_240701
-331,gpt_3.5_turbo_1106,if_lb,51.53,[],livebench_240701
-332,command_r_plus,if_lb,71.51,[],livebench_240701
-333,mistral_small_2402,if_lb,63.91,[],livebench_240701
-334,gemma_2_9b_it,if_lb,61.55,[],livebench_240701
-335,phi_3_medium_4k_instruct,if_lb,53.3,[],livebench_240701
-336,phi_3_medium_128k_instruct,if_lb,56.15,[],livebench_240701
-337,deepseek_coder_v2_lite_instruct,if_lb,48.34,[],livebench_240701
-338,qwen1.5_110b_chat,if_lb,55.26,[],livebench_240701
-339,qwen1.5_72b_chat,if_lb,58.25,[],livebench_240701
-340,command_r,if_lb,57.16,[],livebench_240701
-341,phi_3_small_128k_instruct,if_lb,36.88,[],livebench_240701
-342,meta_llama_3_8b_instruct,if_lb,57.14,[],livebench_240701
-343,qwen2_7b_instruct,if_lb,44.74,[],livebench_240701
-344,phi_3_small_8k_instruct,if_lb,48.24,[],livebench_240701
-345,openhermes_2.5_mistral_7b,if_lb,52.78,[],livebench_240701
-346,mixtral_8x7b_instruct_v0.1,if_lb,44.81,[],livebench_240701
-347,mistral_7b_instruct_v0.2,if_lb,51.65,[],livebench_240701
-348,phi_3_mini_4k_instruct,if_lb,40.05,[],livebench_240701
-349,zephyr_7b_alpha,if_lb,52.79,[],livebench_240701
-350,phi_3_mini_128k_instruct,if_lb,49.65,[],livebench_240701
-351,zephyr_7b_beta,if_lb,48.32,[],livebench_240701
-352,deepseek_v2_lite_chat,if_lb,41.83,[],livebench_240701
-353,qwen1.5_7b_chat,if_lb,44.12,[],livebench_240701
-354,starling_lm_7b_beta,if_lb,38.32,[],livebench_240701
-355,vicuna_7b_v1.5_16k,if_lb,42.12,[],livebench_240701
-356,vicuna_7b_v1.5,if_lb,41.75,[],livebench_240701
-357,qwen1.5_4b_chat,if_lb,27.75,[],livebench_240701
-358,llama_2_7b_chat,if_lb,44.88,[],livebench_240701
-359,qwen2_1.5b_instruct,if_lb,25.9,[],livebench_240701
-360,yi_6b_chat,if_lb,27.22,[],livebench_240701
-361,qwen2_0.5b_instruct,if_lb,26.63,[],livebench_240701
-362,qwen1.5_1.8b_chat,if_lb,22.9,[],livebench_240701
-363,qwen1.5_0.5b_chat,if_lb,21.3,[],livebench_240701

cache/agreements_cache_42471fdfe00c7ff9b0aba18b66ab5a5f.csv

@@ -0,0 +1,73 @@
+scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
+hellaswag,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+humaneval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+mbpp,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.10540925533894598,0.8005421074231263
+winogrande,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
+planning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+reasoning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+reasoning_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+mathematics_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+if_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+mixeval,mixeval_240601,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+arc_c,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+alpacav2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+arena_elo,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+mmlu,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,humaneval,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,mbpp,BLZ_240312,kendall,top_aggregate,5,0,0.10540925533894598,0.8005421074231263
+aggregate,holistic,winogrande,BLZ_240312,kendall,top_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,top_aggregate,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,planning,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,reasoning,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,reasoning_average,livebench_240701,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,mathematics_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,if_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,mixeval,mixeval_240601,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,arc_c,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,alpacav2,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,arena_elo,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mmlu,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,top_aggregate,5,0,0.6,0.23333333333333334

cache/agreements_cache_6ac32881b7d0a3bf6d8762ff242ff449.csv

@@ -0,0 +1,721 @@
+scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.0,1.0
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.5270462766947298,0.206507295485425
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.5270462766947298,0.206507295485425
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.10540925533894598,0.8005421074231263
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,-0.10540925533894596,0.8005421074231263
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.0,1.0
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9486832980505137,0.02297740150320607
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.0,1.0
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.10540925533894598,0.8005421074231263
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+planning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.0,1.0
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.9486832980505138,0.02297740150320607
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947299,0.206507295485425
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.5270462766947299,0.206507295485425
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,1.0,0.019176729141549043
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9486832980505137,0.02297740150320607
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.5270462766947299,0.206507295485425
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.0,1.0
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.0,1.0
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.8366600265340756,0.05220363534131463
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7378647873726218,0.07697417298126676
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.5270462766947298,0.206507295485425
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.3333333333333333,0.4349833603383296
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.5270462766947299,0.206507295485425
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894596,0.8005421074231263
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.31622776601683794,0.44848886103153174
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,2,0.0,1.0
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.0,1.0
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.5270462766947298,0.206507295485425
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.5270462766947298,0.206507295485425
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,-0.10540925533894596,0.8005421074231263
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.0,1.0
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.0,1.0
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.9486832980505137,0.02297740150320607
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.0,1.0
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,planning,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.0,1.0
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.9486832980505138,0.02297740150320607
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.5270462766947299,0.206507295485425
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.5270462766947299,0.206507295485425
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,1.0,0.019176729141549043
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.9486832980505137,0.02297740150320607
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.0,1.0
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.5270462766947299,0.206507295485425
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.0,1.0
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.0,1.0
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.8366600265340756,0.05220363534131463
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.7378647873726218,0.07697417298126676
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.5270462766947298,0.206507295485425
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.3333333333333333,0.4349833603383296
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.5270462766947299,0.206507295485425
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.10540925533894596,0.8005421074231263
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.31622776601683794,0.44848886103153174
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,2,0.0,1.0
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334

cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv

@@ -0,0 +1,721 @@
+scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425
+mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+planning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0
+planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7378647873726218,0.07697417298126676
+llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425
+aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,planning,biggen_240612,kendall,random,5,0,0.0,1.0
+aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.7378647873726218,0.07697417298126676
+aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333

cache/agreements_cache_a8b645e4d5ba862fbfa9ef3ecf73b44c.csv

@@ -0,0 +1,721 @@
+scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+hellaswag,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.5270462766947298,0.206507295485425
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.5270462766947298,0.206507295485425
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.5270462766947298,0.206507295485425
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.22360679774997896,0.6015081344405899
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.10540925533894598,0.8005421074231263
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+humaneval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.22360679774997896,0.6015081344405899
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.31622776601683794,0.44848886103153174
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.31622776601683794,0.44848886103153174
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.10540925533894598,0.8005421074231263
+mbpp,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.19999999999999998,0.8166666666666667
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
+winogrande,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.9486832980505137,0.02297740150320607
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+grounding,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.8944271909999159,0.0367138563627041
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.9486832980505137,0.02297740150320607
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.0,1.0
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.8944271909999159,0.0367138563627041
+instruction_following,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+planning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
+reasoning,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+refinement,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+safety,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.0,1.0
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.5270462766947298,0.206507295485425
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7378647873726218,0.07697417298126676
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+reasoning_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+coding_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+mathematics_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
+if_average,livebench_240701,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.9999999999999999,0.016666666666666666
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+mixeval,mixeval_240601,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+agieval,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.0,1.0
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+arc_c,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.31622776601683794,0.44848886103153174
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.31622776601683794,0.44848886103153174
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
+alpacav2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.0,1.0
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.0,1.0
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,-0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.31622776601683794,0.44848886103153174
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+arena_elo,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.39999999999999997,0.48333333333333334
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.0,1.0
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,-0.39999999999999997,0.48333333333333334
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+bbh,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.0,1.0
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+gpt4all,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,-0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
+hugging_6,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.11952286093343936,0.7815112949987133
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.35856858280031806,0.40538055645894233
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.31622776601683794,0.44848886103153174
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.0,1.0
+llmonitor,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,-0.10540925533894598,0.8005421074231263
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+magi,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.0,1.0
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+mmlu,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.0,1.0
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.10540925533894598,0.8005421074231263
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+mt_bench,BLZ_240312,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,0,0.0,1.0
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.5270462766947298,0.206507295485425
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,2,0.5270462766947298,0.206507295485425
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,3,0.5270462766947298,0.206507295485425
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.22360679774997896,0.6015081344405899
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,humaneval,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.22360679774997896,0.6015081344405899
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,0,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.31622776601683794,0.44848886103153174
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.31622776601683794,0.44848886103153174
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,3,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,5,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,8,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mbpp,BLZ_240312,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
+aggregate,holistic,winogrande,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,4,0.9486832980505137,0.02297740150320607
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,grounding,biggen_240612,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,0,0.0,1.0
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,4,0.8944271909999159,0.0367138563627041
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,5,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,6,0.9486832980505137,0.02297740150320607
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,7,0.0,1.0
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,8,0.8944271909999159,0.0367138563627041
+aggregate,holistic,instruction_following,biggen_240612,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,planning,biggen_240612,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,8,0.0,1.0
+aggregate,holistic,reasoning,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,refinement,biggen_240612,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,0,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,1,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,3,0.0,1.0
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,4,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,safety,biggen_240612,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,3,0.0,1.0
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,7,0.0,1.0
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,2,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.7378647873726218,0.07697417298126676
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+aggregate,holistic,reasoning_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+aggregate,holistic,coding_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,mathematics_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,0,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,3,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,8,0.0,1.0
+aggregate,holistic,if_average,livebench_240701,kendall,somewhere_aggregate,5,9,0.19999999999999998,0.8166666666666667
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,1,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,4,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,7,0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,1,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,8,0.7999999999999999,0.08333333333333333
+aggregate,holistic,mixeval,mixeval_240601,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,4,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,5,0.9999999999999999,0.016666666666666666
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,6,0.19999999999999998,0.8166666666666667
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,7,0.19999999999999998,0.8166666666666667
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,agieval,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,4,0.0,1.0
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,6,0.31622776601683794,0.44848886103153174
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arc_c,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7378647873726218,0.07697417298126676
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.31622776601683794,0.44848886103153174
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7378647873726218,0.07697417298126676
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,somewhere_aggregate,5,9,0.31622776601683794,0.44848886103153174
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,2,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,3,0.7378647873726218,0.07697417298126676
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,5,-0.6,0.23333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
+aggregate,holistic,alpacav2,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,0,0.0,1.0
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,2,0.7999999999999999,0.08333333333333333
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,3,0.0,1.0
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,somewhere_aggregate,5,9,0.0,1.0
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,1,0.6,0.23333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,3,-0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,5,0.31622776601683794,0.44848886103153174
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.9999999999999999,0.016666666666666666
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,arena_elo,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,0,0.9486832980505137,0.02297740150320607
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,1,0.31622776601683794,0.44848886103153174
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,3,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,4,0.0,1.0
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,5,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,6,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,8,0.5270462766947298,0.206507295485425
+aggregate,holistic,bbh,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,3,0.0,1.0
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,4,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,2,0.31622776601683794,0.44848886103153174
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,4,0.31622776601683794,0.44848886103153174
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,8,0.39999999999999997,0.48333333333333334
+aggregate,holistic,gpt4all,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,0,-0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,1,-0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,4,0.19999999999999998,0.8166666666666667
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,6,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.6,0.23333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,8,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,hugging_6,BLZ_240312,kendall,somewhere_aggregate,5,9,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,0,0.11952286093343936,0.7815112949987133
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,1,0.0,1.0
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,6,0.35856858280031806,0.40538055645894233
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,7,0.31622776601683794,0.44848886103153174
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,8,0.0,1.0
+aggregate,holistic,llmonitor,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,1,0.19999999999999998,0.8166666666666667
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,2,-0.10540925533894598,0.8005421074231263
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,5,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,7,0.7999999999999999,0.08333333333333333
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,magi,BLZ_240312,kendall,somewhere_aggregate,5,9,-0.19999999999999998,0.8166666666666667
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,2,0.0,1.0
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,5,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,6,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,7,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,mmlu,BLZ_240312,kendall,somewhere_aggregate,5,9,0.5270462766947298,0.206507295485425
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,1,0.0,1.0
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,2,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,3,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,4,0.39999999999999997,0.48333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,5,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,6,0.10540925533894598,0.8005421074231263
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,7,-0.39999999999999997,0.48333333333333334
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,8,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mt_bench,BLZ_240312,kendall,somewhere_aggregate,5,9,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,1,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,2,0.19999999999999998,0.8166666666666667
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,3,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,4,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,5,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,6,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,7,0.39999999999999997,0.48333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,8,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,somewhere_aggregate,5,9,0.7999999999999999,0.08333333333333333

cache/agreements_cache_facdc1028ee0edd9aed491afc51b884d.csv

@@ -0,0 +1,73 @@
+scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
+hellaswag,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+humaneval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+mbpp,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+winogrande,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+grounding,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+instruction_following,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+planning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+reasoning,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+refinement,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+safety,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+theory_of_mind,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+tool_usage,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+livebench_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+reasoning_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+coding_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+mathematics_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+data_analysis_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+language_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+if_average,livebench_240701,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+arena_hard,arena_hard_2404,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+mixeval,mixeval_240601,aggregate,holistic,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+agieval,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+arc_c,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+alpacav1,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+alpacav2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+arena_elo,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+bbh,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+eq_benchv2,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+gpt4all,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.0,1.0
+hugging_6,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+llmonitor,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+magi,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+mmlu,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+mt_bench,BLZ_240312,aggregate,holistic,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+biggen_mwr,biggen_240612,aggregate,holistic,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,hellaswag,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,humaneval,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,mbpp,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,winogrande,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,grounding,biggen_240612,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,instruction_following,biggen_240612,kendall,top_aggregate,5,0,0.7378647873726218,0.07697417298126676
+aggregate,holistic,planning,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,reasoning,biggen_240612,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,refinement,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,safety,biggen_240612,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,theory_of_mind,biggen_240612,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,tool_usage,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,livebench_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,reasoning_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,coding_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mathematics_average,livebench_240701,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,data_analysis_average,livebench_240701,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,language_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,if_average,livebench_240701,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,arena_hard,arena_hard_2404,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,mixeval,mixeval_240601,kendall,top_aggregate,5,0,0.7999999999999999,0.08333333333333333
+aggregate,holistic,agieval,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,arc_c,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,alpacav1,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,alpacav2,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,arena_elo,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,bbh,BLZ_240312,kendall,top_aggregate,5,0,0.5270462766947298,0.206507295485425
+aggregate,holistic,eq_benchv2,BLZ_240312,kendall,top_aggregate,5,0,0.9999999999999999,0.016666666666666666
+aggregate,holistic,gpt4all,BLZ_240312,kendall,top_aggregate,5,0,0.0,1.0
+aggregate,holistic,hugging_6,BLZ_240312,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334
+aggregate,holistic,llmonitor,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,magi,BLZ_240312,kendall,top_aggregate,5,0,0.31622776601683794,0.44848886103153174
+aggregate,holistic,mmlu,BLZ_240312,kendall,top_aggregate,5,0,0.19999999999999998,0.8166666666666667
+aggregate,holistic,mt_bench,BLZ_240312,kendall,top_aggregate,5,0,0.6,0.23333333333333334
+aggregate,holistic,biggen_mwr,biggen_240612,kendall,top_aggregate,5,0,0.39999999999999997,0.48333333333333334

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/IBM/benchbench.git
+streamlit
+plotly