update score

src/detail_math_score.json

@@ -1,5 +1,5 @@
 {
-    "time": "2025-01-23 09:27:24",
+    "time": "2025-01-23 11:23:17",
     "results": {
         "IO": {
             "gpt-3.5-turbo": {
@@ -22,7 +22,7 @@
                     "Average output tokens": 30
                 },
                 "AQuA": {
-                    "Score": 38.97,
+                    "Score": 38.98,
                     "Pass rate": 1.0,
                     "Cost($)": 0.038,
                     "Framework": "",
@@ -122,7 +122,7 @@
                 },
                 "AQuA": {
                     "Score": 84.25,
-                    "Pass rate": 0.996,
+                    "Pass rate": 0.9961,
                     "Cost($)": 0.0742,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -141,7 +141,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 92.26,
+                    "Score": 92.27,
                     "Pass rate": 1.0,
                     "Cost($)": 0.4709,
                     "Framework": "",
@@ -154,7 +154,7 @@
                     "Average output tokens": 191
                 },
                 "AQuA": {
-                    "Score": 82.67,
+                    "Score": 82.68,
                     "Pass rate": 0.9921,
                     "Cost($)": 0.0798,
                     "Framework": "",
@@ -188,7 +188,7 @@
                 },
                 "AQuA": {
                     "Score": 78.74,
-                    "Pass rate": 0.9842,
+                    "Pass rate": 0.9843,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -208,7 +208,7 @@
                 },
                 "gsm8k": {
                     "Score": 57.16,
-                    "Pass rate": 0.9954,
+                    "Pass rate": 0.9955,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -221,7 +221,7 @@
                 },
                 "AQuA": {
                     "Score": 51.18,
-                    "Pass rate": 0.9881,
+                    "Pass rate": 0.9882,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -240,7 +240,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 11.59,
+                    "Score": 11.6,
                     "Pass rate": 0.9795,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -253,7 +253,7 @@
                     "Average output tokens": 329
                 },
                 "AQuA": {
-                    "Score": 47.63,
+                    "Score": 47.64,
                     "Pass rate": 0.9094,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -273,7 +273,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 16.67,
+                    "Score": 16.68,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -287,7 +287,7 @@
                 },
                 "AQuA": {
                     "Score": 29.13,
-                    "Pass rate": 0.9763,
+                    "Pass rate": 0.9764,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -306,7 +306,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 14.7,
+                    "Score": 14.71,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -319,8 +319,8 @@
                     "Average output tokens": 202
                 },
                 "AQuA": {
-                    "Score": 27.16,
-                    "Pass rate": 0.9881,
+                    "Score": 27.17,
+                    "Pass rate": 0.9882,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -341,7 +341,7 @@
                     "Eval Date": "2025/1/7"
                 },
                 "gsm8k": {
-                    "Score": 74.9,
+                    "Score": 74.91,
                     "Pass rate": 0.9939,
                     "Cost($)": 3.4633,
                     "Framework": "",
@@ -354,7 +354,7 @@
                     "Average output tokens": 106
                 },
                 "AQuA": {
-                    "Score": 64.56,
+                    "Score": 64.57,
                     "Pass rate": 0.9803,
                     "Cost($)": 0.4928,
                     "Framework": "",
@@ -374,7 +374,7 @@
                     "Eval Date": "2025/1/7"
                 },
                 "gsm8k": {
-                    "Score": 85.59,
+                    "Score": 85.6,
                     "Pass rate": 0.9962,
                     "Cost($)": 0.2512,
                     "Framework": "",
@@ -387,7 +387,7 @@
                     "Average output tokens": 104
                 },
                 "AQuA": {
-                    "Score": 77.55,
+                    "Score": 77.56,
                     "Pass rate": 0.9606,
                     "Cost($)": 0.0445,
                     "Framework": "",
@@ -407,8 +407,8 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 63.3,
-                    "Pass rate": 0.9954,
+                    "Score": 63.31,
+                    "Pass rate": 0.9955,
                     "Cost($)": 39.0751,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -453,7 +453,7 @@
                     "Average output tokens": 417
                 },
                 "AQuA": {
-                    "Score": 73.22,
+                    "Score": 73.23,
                     "Pass rate": 1.0,
                     "Cost($)": 0.3177,
                     "Framework": "",
@@ -477,7 +477,7 @@
                     "Pass rate": 0.9992,
                     "Cost($)": 10.1124,
                     "Framework": "",
-                    "X-shot": "",
+                    "X-shot": "8.0",
                     "Samples": 1319,
                     "All tokens": 17937864,
                     "Total input tokens": 17038928,
@@ -487,7 +487,7 @@
                 },
                 "AQuA": {
                     "Score": 79.13,
-                    "Pass rate": 0.996,
+                    "Pass rate": 0.9961,
                     "Cost($)": 0.768,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -506,7 +506,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 82.86,
+                    "Score": 82.87,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -519,7 +519,7 @@
                     "Average output tokens": 375
                 },
                 "AQuA": {
-                    "Score": 74.4,
+                    "Score": 74.41,
                     "Pass rate": 0.9921,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -539,8 +539,8 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 67.77,
-                    "Pass rate": 0.9855,
+                    "Score": 67.78,
+                    "Pass rate": 0.9856,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -576,7 +576,7 @@
                     "Pass rate": 0.9795,
                     "Cost($)": 0.0,
                     "Framework": "",
-                    "X-shot": "",
+                    "X-shot": "8.0",
                     "Samples": 1319,
                     "All tokens": 35669989,
                     "Total input tokens": 30120070,
@@ -605,7 +605,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 24.86,
+                    "Score": 24.87,
                     "Pass rate": 0.8021,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -638,7 +638,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 7.65,
+                    "Score": 7.66,
                     "Pass rate": 0.9522,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -651,7 +651,7 @@
                     "Average output tokens": 2245
                 },
                 "AQuA": {
-                    "Score": 24.01,
+                    "Score": 24.02,
                     "Pass rate": 0.9685,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -673,7 +673,7 @@
                     "Eval Date": "2025/1/7"
                 },
                 "gsm8k": {
-                    "Score": 76.87,
+                    "Score": 76.88,
                     "Pass rate": 0.9924,
                     "Cost($)": 0.6902,
                     "Framework": "",
@@ -686,7 +686,7 @@
                     "Average output tokens": 73
                 },
                 "AQuA": {
-                    "Score": 59.44,
+                    "Score": 59.45,
                     "Pass rate": 1.0,
                     "Cost($)": 0.1748,
                     "Framework": "",
@@ -706,7 +706,7 @@
                     "Eval Date": "2025/1/7"
                 },
                 "gsm8k": {
-                    "Score": 79.6,
+                    "Score": 79.61,
                     "Pass rate": 0.9257,
                     "Cost($)": 0.0576,
                     "Framework": "",
@@ -752,7 +752,7 @@
                     "Average output tokens": 111
                 },
                 "AQuA": {
-                    "Score": 75.19,
+                    "Score": 75.2,
                     "Pass rate": 1.0,
                     "Cost($)": 1.6087,
                     "Framework": "",
@@ -785,7 +785,7 @@
                     "Average output tokens": 110
                 },
                 "AQuA": {
-                    "Score": 75.19,
+                    "Score": 75.2,
                     "Pass rate": 1.0,
                     "Cost($)": 0.1645,
                     "Framework": "",
@@ -805,8 +805,8 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 73.08,
-                    "Pass rate": 0.796,
+                    "Score": 73.09,
+                    "Pass rate": 0.7961,
                     "Cost($)": 0.9736,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -818,7 +818,7 @@
                     "Average output tokens": 456
                 },
                 "AQuA": {
-                    "Score": 79.52,
+                    "Score": 79.53,
                     "Pass rate": 0.9921,
                     "Cost($)": 0.1746,
                     "Framework": "",
@@ -839,7 +839,7 @@
                 },
                 "gsm8k": {
                     "Score": 58.83,
-                    "Pass rate": 0.705,
+                    "Pass rate": 0.7051,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -871,7 +871,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 38.66,
+                    "Score": 38.67,
                     "Pass rate": 0.5542,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -918,7 +918,7 @@
                 },
                 "AQuA": {
                     "Score": 36.61,
-                    "Pass rate": 0.9881,
+                    "Pass rate": 0.9882,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -937,8 +937,8 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 18.49,
-                    "Pass rate": 0.31,
+                    "Score": 18.5,
+                    "Pass rate": 0.3101,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -950,8 +950,8 @@
                     "Average output tokens": 133
                 },
                 "AQuA": {
-                    "Score": 30.7,
-                    "Pass rate": 0.9645,
+                    "Score": 30.71,
+                    "Pass rate": 0.9646,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -984,7 +984,7 @@
                 },
                 "AQuA": {
                     "Score": 17.32,
-                    "Pass rate": 0.9212,
+                    "Pass rate": 0.9213,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1005,7 +1005,7 @@
                     "Eval Date": "2025/1/7"
                 },
                 "gsm8k": {
-                    "Score": 78.69,
+                    "Score": 78.7,
                     "Pass rate": 1.0,
                     "Cost($)": 0.6788,
                     "Framework": "",
@@ -1051,7 +1051,7 @@
                     "Average output tokens": 121
                 },
                 "AQuA": {
-                    "Score": 82.67,
+                    "Score": 82.68,
                     "Pass rate": 0.9724,
                     "Cost($)": 0.0066,
                     "Framework": "",
@@ -1071,7 +1071,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 94.08,
+                    "Score": 94.09,
                     "Pass rate": 1.0,
                     "Cost($)": 4.5367,
                     "Framework": "",
@@ -1084,7 +1084,7 @@
                     "Average output tokens": 164
                 },
                 "AQuA": {
-                    "Score": 82.67,
+                    "Score": 82.68,
                     "Pass rate": 0.9803,
                     "Cost($)": 1.0417,
                     "Framework": "",
@@ -1151,7 +1151,7 @@
                 },
                 "AQuA": {
                     "Score": 83.46,
-                    "Pass rate": 0.9842,
+                    "Pass rate": 0.9843,
                     "Cost($)": 0.0927,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1183,8 +1183,8 @@
                     "Average output tokens": 186
                 },
                 "AQuA": {
-                    "Score": 80.7,
-                    "Pass rate": 0.996,
+                    "Score": 80.71,
+                    "Pass rate": 0.9961,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1203,7 +1203,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 75.43,
+                    "Score": 75.44,
                     "Pass rate": 0.9992,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1216,7 +1216,7 @@
                     "Average output tokens": 196
                 },
                 "AQuA": {
-                    "Score": 60.62,
+                    "Score": 60.63,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1237,7 +1237,7 @@
                 },
                 "gsm8k": {
                     "Score": 77.71,
-                    "Pass rate": 0.9969,
+                    "Pass rate": 0.997,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -1249,7 +1249,7 @@
                     "Average output tokens": 177
                 },
                 "AQuA": {
-                    "Score": 52.75,
+                    "Score": 52.76,
                     "Pass rate": 0.8937,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1269,7 +1269,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 55.49,
+                    "Score": 55.5,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1283,7 +1283,7 @@
                 },
                 "AQuA": {
                     "Score": 40.55,
-                    "Pass rate": 0.9881,
+                    "Pass rate": 0.9882,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1302,7 +1302,7 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 35.93,
+                    "Score": 35.94,
                     "Pass rate": 0.9992,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1316,7 +1316,7 @@
                 },
                 "AQuA": {
                     "Score": 33.07,
-                    "Pass rate": 0.9881,
+                    "Pass rate": 0.9882,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1449,8 +1449,8 @@
                     "Average output tokens": 1723
                 },
                 "AQuA": {
-                    "Score": 85.82,
-                    "Pass rate": 0.9842,
+                    "Score": 85.83,
+                    "Pass rate": 0.9843,
                     "Cost($)": 0.5576,
                     "Framework": "",
                     "X-shot": "0.0",
@@ -1503,7 +1503,7 @@
                 },
                 "gsm8k": {
                     "Score": 88.32,
-                    "Pass rate": 0.9984,
+                    "Pass rate": 0.9985,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -1515,7 +1515,7 @@
                     "Average output tokens": 1900
                 },
                 "AQuA": {
-                    "Score": 81.49,
+                    "Score": 81.5,
                     "Pass rate": 1.0,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1535,8 +1535,8 @@
                     "Eval Date": "2025/1/22"
                 },
                 "gsm8k": {
-                    "Score": 75.2,
-                    "Pass rate": 0.9954,
+                    "Score": 75.21,
+                    "Pass rate": 0.9955,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -1548,7 +1548,7 @@
                     "Average output tokens": 2358
                 },
                 "AQuA": {
-                    "Score": 53.14,
+                    "Score": 53.15,
                     "Pass rate": 0.9606,
                     "Cost($)": 0.0,
                     "Framework": "",
@@ -1569,7 +1569,7 @@
                 },
                 "gsm8k": {
                     "Score": 41.39,
-                    "Pass rate": 0.9825,
+                    "Pass rate": 0.9826,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "8.0",
@@ -1647,8 +1647,8 @@
                     "Average output tokens": 3036
                 },
                 "AQuA": {
-                    "Score": 30.7,
-                    "Pass rate": 0.9842,
+                    "Score": 30.71,
+                    "Pass rate": 0.9843,
                     "Cost($)": 0.0,
                     "Framework": "",
                     "X-shot": "0.0",

src/detail_results.csv

@@ -2,100 +2,100 @@ Rank,Algorithm,Dataset,LLM,Eval Date,Score,Pass rate,X-shot,Cost($),Framework,Sa
 1,SC-CoT,AQuA,gpt-4o,2025/1/22,88.19,1.0,0.0,6.2412,,254,678811,72916,287,605895,2385
 2,SC-CoT,AQuA,Llama-3.3-70B-Instruct,2025/1/22,86.61,0.9921,0.0,0.5847,,254,1037124,283248,1115,753876,2968
 3,CoT,AQuA,Qwen2.5-72B-Instruct,2025/1/22,86.22,0.9921,0.0,0.0808,,254,143289,25143,99,118146,465
-4,SC-CoT,AQuA,Qwen2.5-72B-Instruct,2025/1/22,85.82,0.9842,0.0,0.5576,,254,989058,241149,949,747909,2945
-5,IO,AQuA,Qwen2.5-72B-Instruct,2025/1/22,84.25,0.996,0.0,0.0742,,254,131604,25397,100,106207,418
-6,CoT,AQuA,Llama-3.3-70B-Instruct,2025/1/22,83.46,0.9842,0.0,0.0927,,254,164389,32555,128,131834,519
-7,IO,AQuA,Llama-3.3-70B-Instruct,2025/1/22,82.67,0.9921,0.0,0.0798,,254,141567,32809,129,108758,428
-8,CoT,AQuA,Doubao-lite-32k,2025/1/7,82.67,0.9724,0.0,0.0066,,254,94577,27978,110,66599,262
-9,CoT,AQuA,gpt-4o,2025/1/22,82.67,0.9803,0.0,1.0417,,254,123017,25123,99,97894,385
+4,SC-CoT,AQuA,Qwen2.5-72B-Instruct,2025/1/22,85.83,0.9843,0.0,0.5576,,254,989058,241149,949,747909,2945
+5,IO,AQuA,Qwen2.5-72B-Instruct,2025/1/22,84.25,0.9961,0.0,0.0742,,254,131604,25397,100,106207,418
+6,CoT,AQuA,Llama-3.3-70B-Instruct,2025/1/22,83.46,0.9843,0.0,0.0927,,254,164389,32555,128,131834,519
+7,IO,AQuA,Llama-3.3-70B-Instruct,2025/1/22,82.68,0.9921,0.0,0.0798,,254,141567,32809,129,108758,428
+8,CoT,AQuA,Doubao-lite-32k,2025/1/7,82.68,0.9724,0.0,0.0066,,254,94577,27978,110,66599,262
+9,CoT,AQuA,gpt-4o,2025/1/22,82.68,0.9803,0.0,1.0417,,254,123017,25123,99,97894,385
 10,SC-CoT,AQuA,Doubao-lite-32k,2025/1/7,81.5,0.9764,0.0,0.0347,,254,465846,83830,330,382016,1504
-11,SC-CoT,AQuA,Qwen2.5-7B-Instruct,2025/1/22,81.49,1.0,0.0,0.0,,254,1015368,278848,1098,736520,2900
-12,CoT,AQuA,Qwen2.5-7B-Instruct,2025/1/22,80.7,0.996,0.0,0.0,,254,149736,33017,130,116719,460
-13,PoT,AQuA,Llama-3.3-70B-Instruct,2025/1/22,79.52,0.9921,0.0,0.1746,,254,309799,240735,948,69064,272
+11,SC-CoT,AQuA,Qwen2.5-7B-Instruct,2025/1/22,81.5,1.0,0.0,0.0,,254,1015368,278848,1098,736520,2900
+12,CoT,AQuA,Qwen2.5-7B-Instruct,2025/1/22,80.71,0.9961,0.0,0.0,,254,149736,33017,130,116719,460
+13,PoT,AQuA,Llama-3.3-70B-Instruct,2025/1/22,79.53,0.9921,0.0,0.1746,,254,309799,240735,948,69064,272
 14,IO,AQuA,Doubao-lite-32k,2025/1/7,79.13,1.0,0.0,0.0058,,254,87742,33058,130,54684,215
-15,ReAct-Pro*,AQuA,Llama-3.3-70B-Instruct,2025/1/22,79.13,0.996,0.0,0.768,,254,1362379,1119143,4406,243236,958
-16,IO,AQuA,Qwen2.5-7B-Instruct,2025/1/22,78.74,0.9842,0.0,0.0,,254,137771,33271,131,104500,411
-17,ReAct-Pro*,AQuA,Doubao-lite-32k,2025/1/7,77.55,0.9606,0.0,0.0445,,254,1032841,977890,3850,54951,216
+15,ReAct-Pro*,AQuA,Llama-3.3-70B-Instruct,2025/1/22,79.13,0.9961,0.0,0.768,,254,1362379,1119143,4406,243236,958
+16,IO,AQuA,Qwen2.5-7B-Instruct,2025/1/22,78.74,0.9843,0.0,0.0,,254,137771,33271,131,104500,411
+17,ReAct-Pro*,AQuA,Doubao-lite-32k,2025/1/7,77.56,0.9606,0.0,0.0445,,254,1032841,977890,3850,54951,216
 18,IO,AQuA,gpt-4o,2025/1/22,75.59,0.9724,0.0,1.1453,,254,133752,25631,101,108121,426
-19,PoT,AQuA,gpt-4o,2025/1/22,75.19,1.0,0.0,1.6087,,254,327908,222717,877,105191,414
-20,PoT,AQuA,Qwen2.5-72B-Instruct,2025/1/22,75.19,1.0,0.0,0.1645,,254,291764,249215,981,42549,168
-21,ReAct-Pro*,AQuA,Qwen2.5-7B-Instruct,2025/1/22,74.4,0.9921,0.0,0.0,,254,695844,564165,2221,131679,518
-22,ReAct-Pro*,AQuA,Qwen2.5-72B-Instruct,2025/1/22,73.22,1.0,0.0,0.3177,,254,563603,441765,1739,121838,480
+19,PoT,AQuA,gpt-4o,2025/1/22,75.2,1.0,0.0,1.6087,,254,327908,222717,877,105191,414
+20,PoT,AQuA,Qwen2.5-72B-Instruct,2025/1/22,75.2,1.0,0.0,0.1645,,254,291764,249215,981,42549,168
+21,ReAct-Pro*,AQuA,Qwen2.5-7B-Instruct,2025/1/22,74.41,0.9921,0.0,0.0,,254,695844,564165,2221,131679,518
+22,ReAct-Pro*,AQuA,Qwen2.5-72B-Instruct,2025/1/22,73.23,1.0,0.0,0.3177,,254,563603,441765,1739,121838,480
 23,PoT,AQuA,Doubao-lite-32k,2025/1/7,71.65,0.9685,0.0,0.0147,,254,309436,259863,1023,49573,195
 24,SC-CoT,AQuA,gpt-3.5-turbo,2025/1/7,70.47,0.9882,0.0,0.5578,,254,418617,70157,276,348460,1372
 25,PoT,AQuA,Qwen2.5-7B-Instruct,2025/1/22,68.11,1.0,0.0,0.0,,254,313728,264517,1041,49211,194
-26,ReAct-Pro*,AQuA,gpt-3.5-turbo,2025/1/7,64.56,0.9803,0.0,0.4928,,254,903587,862614,3396,40973,161
+26,ReAct-Pro*,AQuA,gpt-3.5-turbo,2025/1/7,64.57,0.9803,0.0,0.4928,,254,903587,862614,3396,40973,161
 27,CoT,AQuA,gpt-3.5-turbo,2025/1/7,61.02,0.937,0.0,0.0957,,254,80793,25447,100,55346,218
-28,CoT,AQuA,Llama-3.1-8B-Instruct,2025/1/22,60.62,1.0,0.0,0.0,,254,144435,32555,128,111880,440
-29,PoT,AQuA,gpt-3.5-turbo,2025/1/7,59.44,1.0,0.0,0.1748,,254,266654,225162,886,41492,163
+28,CoT,AQuA,Llama-3.1-8B-Instruct,2025/1/22,60.63,1.0,0.0,0.0,,254,144435,32555,128,111880,440
+29,PoT,AQuA,gpt-3.5-turbo,2025/1/7,59.45,1.0,0.0,0.1748,,254,266654,225162,886,41492,163
 30,ReAct-Pro*,AQuA,gpt-4o,2025/1/22,57.48,0.9724,0.0,2.304,,254,692096,615589,2424,76507,301
 31,ReAct-Pro*,AQuA,Llama-3.1-8B-Instruct,2025/1/22,55.51,0.9685,0.0,0.0,,254,4340821,3764723,14822,576098,2268
-32,SC-CoT,AQuA,Llama-3.1-8B-Instruct,2025/1/22,53.14,0.9606,0.0,0.0,,254,1041346,372968,1468,668378,2631
-33,CoT,AQuA,Internllm2_5-7B,2025/1/22,52.75,0.8937,0.0,0.0,,254,127520,26610,105,100910,397
-34,IO,AQuA,Llama-3.1-8B-Instruct,2025/1/22,51.18,0.9881,0.0,0.0,,254,133106,26459,104,106647,420
-35,IO,AQuA,Internllm2_5-7B,2025/1/22,47.63,0.9094,0.0,0.0,,254,185041,50232,198,134809,531
+32,SC-CoT,AQuA,Llama-3.1-8B-Instruct,2025/1/22,53.15,0.9606,0.0,0.0,,254,1041346,372968,1468,668378,2631
+33,CoT,AQuA,Internllm2_5-7B,2025/1/22,52.76,0.8937,0.0,0.0,,254,127520,26610,105,100910,397
+34,IO,AQuA,Llama-3.1-8B-Instruct,2025/1/22,51.18,0.9882,0.0,0.0,,254,133106,26459,104,106647,420
+35,IO,AQuA,Internllm2_5-7B,2025/1/22,47.64,0.9094,0.0,0.0,,254,185041,50232,198,134809,531
 36,ReAct-Pro*,AQuA,Internllm2_5-7B,2025/1/22,40.94,0.9685,0.0,0.0,,254,4428801,3592039,14142,836762,3294
-37,CoT,AQuA,Qwen2-1.5B-Instruct,2025/1/22,40.55,0.9881,0.0,0.0,,254,110040,30477,120,79563,313
-38,IO,AQuA,gpt-3.5-turbo,2025/1/7,38.97,1.0,0.0,0.038,,254,42471,25701,101,16770,66
+37,CoT,AQuA,Qwen2-1.5B-Instruct,2025/1/22,40.55,0.9882,0.0,0.0,,254,110040,30477,120,79563,313
+38,IO,AQuA,gpt-3.5-turbo,2025/1/7,38.98,1.0,0.0,0.038,,254,42471,25701,101,16770,66
 39,PoT,AQuA,Llama-3.1-8B-Instruct,2025/1/22,36.61,0.9685,0.0,0.0,,254,290914,240613,947,50301,198
-40,PoT,AQuA,Internllm2_5-7B,2025/1/22,36.61,0.9881,0.0,0.0,,254,301962,233505,919,68457,270
+40,PoT,AQuA,Internllm2_5-7B,2025/1/22,36.61,0.9882,0.0,0.0,,254,301962,233505,919,68457,270
 41,SC-CoT,AQuA,Internllm2_5-7B,2025/1/22,35.85,0.988,0.0,0.0,,254,1240388,530701,2089,709687,2794
-42,CoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,33.07,0.9881,0.0,0.0,,254,117339,30477,120,86862,342
-43,PoT,AQuA,Qwen2-1.5B-Instruct,2025/1/22,30.7,0.9645,0.0,0.0,,254,298475,246560,971,51915,204
-44,SC-CoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,30.7,0.9842,0.0,0.0,,254,1225539,496206,1954,729333,2871
+42,CoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,33.07,0.9882,0.0,0.0,,254,117339,30477,120,86862,342
+43,PoT,AQuA,Qwen2-1.5B-Instruct,2025/1/22,30.71,0.9646,0.0,0.0,,254,298475,246560,971,51915,204
+44,SC-CoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,30.71,0.9843,0.0,0.0,,254,1225539,496206,1954,729333,2871
 45,SC-CoT,AQuA,Qwen2-1.5B-Instruct,2025/1/22,30.31,0.9724,0.0,0.0,,254,1157076,430703,1696,726373,2860
-46,IO,AQuA,Qwen2-1.5B-Instruct,2025/1/22,29.13,0.9763,0.0,0.0,,254,71047,27937,110,43110,170
-47,IO,AQuA,Qwen2-0.5B-Instruct,2025/1/22,27.16,0.9881,0.0,0.0,,254,110415,27937,110,82478,325
+46,IO,AQuA,Qwen2-1.5B-Instruct,2025/1/22,29.13,0.9764,0.0,0.0,,254,71047,27937,110,43110,170
+47,IO,AQuA,Qwen2-0.5B-Instruct,2025/1/22,27.17,0.9882,0.0,0.0,,254,110415,27937,110,82478,325
 48,ReAct-Pro*,AQuA,Qwen2-1.5B-Instruct,2025/1/22,25.59,0.9606,0.0,0.0,,254,5072004,4555858,17936,516146,2032
-49,ReAct-Pro*,AQuA,Qwen2-0.5B-Instruct,2025/1/22,24.01,0.9685,0.0,0.0,,254,7170087,6344167,24977,825920,3252
-50,PoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,17.32,0.9212,0.0,0.0,,254,322281,258867,1019,63414,250
+49,ReAct-Pro*,AQuA,Qwen2-0.5B-Instruct,2025/1/22,24.02,0.9685,0.0,0.0,,254,7170087,6344167,24977,825920,3252
+50,PoT,AQuA,Qwen2-0.5B-Instruct,2025/1/22,17.32,0.9213,0.0,0.0,,254,322281,258867,1019,63414,250
 1,SC-CoT,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,95.45,1.0,8.0,4.5021,,1319,7985996,5406763,4099,2579233,1955
-2,CoT,gsm8k,gpt-4o,2025/1/22,94.08,1.0,8.0,4.5367,,1319,1165166,948668,719,216498,164
+2,CoT,gsm8k,gpt-4o,2025/1/22,94.09,1.0,8.0,4.5367,,1319,1165166,948668,719,216498,164
 3,CoT,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,93.93,1.0,8.0,0.687,,1319,1218665,990168,751,228497,173
 4,PoT,gsm8k,gpt-4o,2025/1/22,93.1,0.9977,8.0,4.2166,,1319,1247912,1101672,835,146240,111
 5,CoT,gsm8k,Qwen2.5-72B-Instruct,2025/1/22,92.87,1.0,8.0,0.7195,,1319,1276252,1005119,762,271133,206
 6,PoT,gsm8k,Qwen2.5-72B-Instruct,2025/1/22,92.34,0.9939,8.0,0.7054,,1319,1251210,1106682,839,144528,110
-7,IO,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,92.26,1.0,8.0,0.4709,,1319,835275,583916,443,251359,191
+7,IO,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,92.27,1.0,8.0,0.4709,,1319,835275,583916,443,251359,191
 8,SC-CoT,gsm8k,gpt-4o,2025/1/22,90.75,1.0,8.0,24.2428,,1319,3300971,1168927,886,2132044,1616
 9,SC-CoT,gsm8k,Qwen2.5-72B-Instruct,2025/1/22,90.67,1.0,8.0,4.2651,,1319,7565637,5292383,4012,2273254,1723
 10,CoT,gsm8k,Doubao-lite-32k,2025/1/7,89.31,1.0,8.0,0.0558,,1319,1201820,1042095,790,159725,121
 11,IO,gsm8k,gpt-4o,2025/1/22,88.4,1.0,8.0,3.3463,,1319,741446,542416,411,199030,151
-12,SC-CoT,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,88.32,0.9984,8.0,0.0,,1319,8173818,5668252,4297,2505566,1900
-13,ReAct-Pro*,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,87.64,0.9992,,10.1124,,1319,17937864,17038928,12918,898936,682
+12,SC-CoT,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,88.32,0.9985,8.0,0.0,,1319,8173818,5668252,4297,2505566,1900
+13,ReAct-Pro*,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,87.64,0.9992,8.0,10.1124,,1319,17937864,17038928,12918,898936,682
 14,ReAct-Pro*,gsm8k,Qwen2.5-72B-Instruct,2025/1/22,87.26,1.0,8.0,10.5479,,1319,18710437,18160983,13769,549454,417
 15,IO,gsm8k,Qwen2.5-72B-Instruct,2025/1/22,86.58,1.0,8.0,0.4899,,1319,869060,555340,421,313720,238
 16,CoT,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,85.67,1.0,8.0,0.0,,1319,1290805,1046008,793,244797,186
-17,ReAct-Pro*,gsm8k,Doubao-lite-32k,2025/1/7,85.59,0.9962,8.0,0.2512,,1319,5998639,5862016,4444,136623,104
+17,ReAct-Pro*,gsm8k,Doubao-lite-32k,2025/1/7,85.6,0.9962,8.0,0.2512,,1319,5998639,5862016,4444,136623,104
 18,SC-CoT,gsm8k,Doubao-lite-32k,2025/1/7,83.7,0.997,8.0,0.155,,1319,2507687,1230019,933,1277668,969
-19,ReAct-Pro*,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,82.86,1.0,8.0,0.0,,1319,14850914,14355752,10884,495162,375
+19,ReAct-Pro*,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,82.87,1.0,8.0,0.0,,1319,14850914,14355752,10884,495162,375
 20,SC-CoT,gsm8k,gpt-3.5-turbo,2025/1/7,82.56,0.9985,8.0,2.6285,,1319,2560697,1212520,919,1348177,1022
-21,PoT,gsm8k,Doubao-lite-32k,2025/1/7,79.6,0.9257,8.0,0.0576,,1319,1288055,1170038,887,118017,89
-22,CoT,gsm8k,gpt-3.5-turbo,2025/1/7,78.69,1.0,8.0,0.6788,,1319,1088041,953242,723,134799,102
-23,CoT,gsm8k,Internllm2_5-7B,2025/1/22,77.71,0.9969,8.0,0.0,,1319,1202163,968163,734,234000,177
-24,PoT,gsm8k,gpt-3.5-turbo,2025/1/7,76.87,0.9924,8.0,0.6902,,1319,1187080,1090418,827,96662,73
-25,CoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,75.43,0.9992,8.0,0.0,,1319,1248329,990168,751,258161,196
-26,SC-CoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,75.2,0.9954,8.0,0.0,,1319,8444203,5334657,4044,3109546,2358
-27,ReAct-Pro*,gsm8k,gpt-3.5-turbo,2025/1/7,74.9,0.9939,8.0,3.4633,,1319,6646286,6506164,4933,140122,106
-28,PoT,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,73.08,0.796,8.0,0.9736,,1319,1727044,1126025,854,601019,456
+21,PoT,gsm8k,Doubao-lite-32k,2025/1/7,79.61,0.9257,8.0,0.0576,,1319,1288055,1170038,887,118017,89
+22,CoT,gsm8k,gpt-3.5-turbo,2025/1/7,78.7,1.0,8.0,0.6788,,1319,1088041,953242,723,134799,102
+23,CoT,gsm8k,Internllm2_5-7B,2025/1/22,77.71,0.997,8.0,0.0,,1319,1202163,968163,734,234000,177
+24,PoT,gsm8k,gpt-3.5-turbo,2025/1/7,76.88,0.9924,8.0,0.6902,,1319,1187080,1090418,827,96662,73
+25,CoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,75.44,0.9992,8.0,0.0,,1319,1248329,990168,751,258161,196
+26,SC-CoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,75.21,0.9955,8.0,0.0,,1319,8444203,5334657,4044,3109546,2358
+27,ReAct-Pro*,gsm8k,gpt-3.5-turbo,2025/1/7,74.91,0.9939,8.0,3.4633,,1319,6646286,6506164,4933,140122,106
+28,PoT,gsm8k,Llama-3.3-70B-Instruct,2025/1/22,73.09,0.7961,8.0,0.9736,,1319,1727044,1126025,854,601019,456
 29,IO,gsm8k,Doubao-lite-32k,2025/1/7,72.02,0.9992,8.0,0.0354,,1319,740483,617377,468,123106,93
-30,ReAct-Pro*,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,67.77,0.9855,8.0,0.0,,1319,22835767,21044978,15955,1790789,1358
-31,ReAct-Pro*,gsm8k,gpt-4o,2025/1/22,63.3,0.9954,8.0,39.0751,,1319,14715887,14411173,10926,304714,231
-32,PoT,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,58.83,0.705,8.0,0.0,,1319,1362822,1145390,868,217432,165
+30,ReAct-Pro*,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,67.78,0.9856,8.0,0.0,,1319,22835767,21044978,15955,1790789,1358
+31,ReAct-Pro*,gsm8k,gpt-4o,2025/1/22,63.31,0.9955,8.0,39.0751,,1319,14715887,14411173,10926,304714,231
+32,PoT,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,58.83,0.7051,8.0,0.0,,1319,1362822,1145390,868,217432,165
 33,IO,gsm8k,Qwen2.5-7B-Instruct,2025/1/22,57.24,1.0,8.0,0.0,,1319,887913,596229,452,291684,221
-34,IO,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,57.16,0.9954,8.0,0.0,,1319,1745429,550941,418,1194488,906
-35,CoT,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,55.49,1.0,8.0,0.0,,1319,1218525,1032818,783,185707,141
-36,SC-CoT,gsm8k,Internllm2_5-7B,2025/1/22,41.39,0.9825,8.0,0.0,,1319,10024857,6674518,5060,3350339,2540
-37,PoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,38.66,0.5542,8.0,0.0,,1319,1391111,1147538,870,243573,185
+34,IO,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,57.16,0.9955,8.0,0.0,,1319,1745429,550941,418,1194488,906
+35,CoT,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,55.5,1.0,8.0,0.0,,1319,1218525,1032818,783,185707,141
+36,SC-CoT,gsm8k,Internllm2_5-7B,2025/1/22,41.39,0.9826,8.0,0.0,,1319,10024857,6674518,5060,3350339,2540
+37,PoT,gsm8k,Llama-3.1-8B-Instruct,2025/1/22,38.67,0.5542,8.0,0.0,,1319,1391111,1147538,870,243573,185
 38,PoT,gsm8k,Internllm2_5-7B,2025/1/22,38.21,0.489,8.0,0.0,,1319,1324949,1136843,862,188106,143
 39,IO,gsm8k,gpt-3.5-turbo,2025/1/7,37.83,0.9992,8.0,0.3328,,1319,586553,546990,415,39563,30
-40,CoT,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,35.93,0.9992,8.0,0.0,,1319,1223459,1032818,783,190641,145
-41,ReAct-Pro*,gsm8k,Internllm2_5-7B,2025/1/22,33.51,0.9795,,0.0,,1319,35669989,30120070,22836,5549919,4208
-42,ReAct-Pro*,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,24.86,0.8021,8.0,0.0,,1319,9828001,9133603,6925,694398,526
-43,PoT,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,18.49,0.31,8.0,0.0,,1319,1327522,1151528,873,175994,133
-44,IO,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,16.67,1.0,8.0,0.0,,1319,736996,568530,431,168466,128
-45,IO,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,14.7,1.0,8.0,0.0,,1319,834897,568116,431,266781,202
-46,IO,gsm8k,Internllm2_5-7B,2025/1/22,11.59,0.9795,8.0,0.0,,1319,1113728,679302,515,434426,329
+40,CoT,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,35.94,0.9992,8.0,0.0,,1319,1223459,1032818,783,190641,145
+41,ReAct-Pro*,gsm8k,Internllm2_5-7B,2025/1/22,33.51,0.9795,8.0,0.0,,1319,35669989,30120070,22836,5549919,4208
+42,ReAct-Pro*,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,24.87,0.8021,8.0,0.0,,1319,9828001,9133603,6925,694398,526
+43,PoT,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,18.5,0.3101,8.0,0.0,,1319,1327522,1151528,873,175994,133
+44,IO,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,16.68,1.0,8.0,0.0,,1319,736996,568530,431,168466,128
+45,IO,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,14.71,1.0,8.0,0.0,,1319,834897,568116,431,266781,202
+46,IO,gsm8k,Internllm2_5-7B,2025/1/22,11.6,0.9795,8.0,0.0,,1319,1113728,679302,515,434426,329
 47,PoT,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,9.62,0.169,8.0,0.0,,1319,1389135,1151528,873,237607,180
-48,ReAct-Pro*,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,7.65,0.9522,8.0,0.0,,1319,55392611,52431343,39751,2961268,2245
+48,ReAct-Pro*,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,7.66,0.9522,8.0,0.0,,1319,55392611,52431343,39751,2961268,2245
 49,SC-CoT,gsm8k,Qwen2-1.5B-Instruct,2025/1/22,5.53,0.8673,8.0,0.0,,1319,8961768,5844218,4431,3117550,2364
 50,SC-CoT,gsm8k,Qwen2-0.5B-Instruct,2025/1/22,3.79,0.9484,8.0,0.0,,1319,10533815,6529832,4951,4003983,3036

src/overall_math_score.json

@@ -1,5 +1,5 @@
 {
-    "time": "2025-01-23 09:27:24",
+    "time": "2025-01-23 11:23:17",
     "results": {
         "IO": {
             "META": {
@@ -12,7 +12,7 @@
                 "Cost($)": 0.3328
             },
             "AQuA": {
-                "Score": 38.97,
+                "Score": 38.98,
                 "Cost($)": 0.038
             }
         },
@@ -23,11 +23,11 @@
                 "Eval Date": "2025/1/7"
             },
             "gsm8k": {
-                "Score": 74.9,
+                "Score": 74.91,
                 "Cost($)": 3.4633
             },
             "AQuA": {
-                "Score": 64.56,
+                "Score": 64.57,
                 "Cost($)": 0.4928
             }
         },
@@ -38,11 +38,11 @@
                 "Eval Date": "2025/1/7"
             },
             "gsm8k": {
-                "Score": 76.87,
+                "Score": 76.88,
                 "Cost($)": 0.6902
             },
             "AQuA": {
-                "Score": 59.44,
+                "Score": 59.45,
                 "Cost($)": 0.1748
             }
         },
@@ -53,7 +53,7 @@
                 "Eval Date": "2025/1/7"
             },
             "gsm8k": {
-                "Score": 78.69,
+                "Score": 78.7,
                 "Cost($)": 0.6788
             },
             "AQuA": {
@@ -98,11 +98,11 @@
                 "Eval Date": "2025/1/7"
             },
             "gsm8k": {
-                "Score": 85.59,
+                "Score": 85.6,
                 "Cost($)": 0.2512
             },
             "AQuA": {
-                "Score": 77.55,
+                "Score": 77.56,
                 "Cost($)": 0.0445
             }
         },
@@ -113,7 +113,7 @@
                 "Eval Date": "2025/1/7"
             },
             "gsm8k": {
-                "Score": 79.6,
+                "Score": 79.61,
                 "Cost($)": 0.0576
             },
             "AQuA": {
@@ -132,7 +132,7 @@
                 "Cost($)": 0.0558
             },
             "AQuA": {
-                "Score": 82.67,
+                "Score": 82.68,
                 "Cost($)": 0.0066
             }
         },
@@ -173,7 +173,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 63.3,
+                "Score": 63.31,
                 "Cost($)": 39.0751
             },
             "AQuA": {
@@ -192,7 +192,7 @@
                 "Cost($)": 4.2166
             },
             "AQuA": {
-                "Score": 75.19,
+                "Score": 75.2,
                 "Cost($)": 1.6087
             }
         },
@@ -203,11 +203,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 94.08,
+                "Score": 94.09,
                 "Cost($)": 4.5367
             },
             "AQuA": {
-                "Score": 82.67,
+                "Score": 82.68,
                 "Cost($)": 1.0417
             }
         },
@@ -252,7 +252,7 @@
                 "Cost($)": 10.5479
             },
             "AQuA": {
-                "Score": 73.22,
+                "Score": 73.23,
                 "Cost($)": 0.3177
             }
         },
@@ -267,7 +267,7 @@
                 "Cost($)": 0.7054
             },
             "AQuA": {
-                "Score": 75.19,
+                "Score": 75.2,
                 "Cost($)": 0.1645
             }
         },
@@ -297,7 +297,7 @@
                 "Cost($)": 4.2651
             },
             "AQuA": {
-                "Score": 85.82,
+                "Score": 85.83,
                 "Cost($)": 0.5576
             }
         },
@@ -308,11 +308,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 92.26,
+                "Score": 92.27,
                 "Cost($)": 0.4709
             },
             "AQuA": {
-                "Score": 82.67,
+                "Score": 82.68,
                 "Cost($)": 0.0798
             }
         },
@@ -338,11 +338,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 73.08,
+                "Score": 73.09,
                 "Cost($)": 0.9736
             },
             "AQuA": {
-                "Score": 79.52,
+                "Score": 79.53,
                 "Cost($)": 0.1746
             }
         },
@@ -398,11 +398,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 82.86,
+                "Score": 82.87,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 74.4,
+                "Score": 74.41,
                 "Cost($)": 0.0
             }
         },
@@ -432,7 +432,7 @@
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 80.7,
+                "Score": 80.71,
                 "Cost($)": 0.0
             }
         },
@@ -447,7 +447,7 @@
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 81.49,
+                "Score": 81.5,
                 "Cost($)": 0.0
             }
         },
@@ -473,7 +473,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 67.77,
+                "Score": 67.78,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -488,7 +488,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 38.66,
+                "Score": 38.67,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -503,11 +503,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 75.43,
+                "Score": 75.44,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 60.62,
+                "Score": 60.63,
                 "Cost($)": 0.0
             }
         },
@@ -518,11 +518,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 75.2,
+                "Score": 75.21,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 53.14,
+                "Score": 53.15,
                 "Cost($)": 0.0
             }
         },
@@ -533,11 +533,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 11.59,
+                "Score": 11.6,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 47.63,
+                "Score": 47.64,
                 "Cost($)": 0.0
             }
         },
@@ -582,7 +582,7 @@
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 52.75,
+                "Score": 52.76,
                 "Cost($)": 0.0
             }
         },
@@ -608,7 +608,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 16.67,
+                "Score": 16.68,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -623,7 +623,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 24.86,
+                "Score": 24.87,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -638,11 +638,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 18.49,
+                "Score": 18.5,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 30.7,
+                "Score": 30.71,
                 "Cost($)": 0.0
             }
         },
@@ -653,7 +653,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 55.49,
+                "Score": 55.5,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -683,11 +683,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 14.7,
+                "Score": 14.71,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 27.16,
+                "Score": 27.17,
                 "Cost($)": 0.0
             }
         },
@@ -698,11 +698,11 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 7.65,
+                "Score": 7.66,
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 24.01,
+                "Score": 24.02,
                 "Cost($)": 0.0
             }
         },
@@ -728,7 +728,7 @@
                 "Eval Date": "2025/1/22"
             },
             "gsm8k": {
-                "Score": 35.93,
+                "Score": 35.94,
                 "Cost($)": 0.0
             },
             "AQuA": {
@@ -747,7 +747,7 @@
                 "Cost($)": 0.0
             },
             "AQuA": {
-                "Score": 30.7,
+                "Score": 30.71,
                 "Cost($)": 0.0
             }
         }

src/overall_results.csv

@@ -3,49 +3,49 @@ Rank,Algorithm,LLM,Eval Date,Avg Score,gsm8k-Score,gsm8k-Cost($),AQuA-Score,AQuA
 2.0,CoT,Qwen2.5-72B-Instruct,2025/1/22,89.55,92.87,0.7195,86.22,0.0808
 3.0,SC-CoT,gpt-4o,2025/1/22,89.47,90.75,24.2428,88.19,6.2412
 4.0,CoT,Llama-3.3-70B-Instruct,2025/1/22,88.70,93.93,0.687,83.46,0.0927
-5.0,CoT,gpt-4o,2025/1/22,88.38,94.08,4.5367,82.67,1.0417
-6.0,SC-CoT,Qwen2.5-72B-Instruct,2025/1/22,88.25,90.67,4.2651,85.82,0.5576
-7.0,IO,Llama-3.3-70B-Instruct,2025/1/22,87.47,92.26,0.4709,82.67,0.0798
-8.0,CoT,Doubao-lite-32k,2025/1/7,85.99,89.31,0.0558,82.67,0.0066
+5.0,CoT,gpt-4o,2025/1/22,88.39,94.09,4.5367,82.68,1.0417
+6.0,SC-CoT,Qwen2.5-72B-Instruct,2025/1/22,88.25,90.67,4.2651,85.83,0.5576
+7.0,IO,Llama-3.3-70B-Instruct,2025/1/22,87.48,92.27,0.4709,82.68,0.0798
+8.0,CoT,Doubao-lite-32k,2025/1/7,86.00,89.31,0.0558,82.68,0.0066
 9.0,IO,Qwen2.5-72B-Instruct,2025/1/22,85.42,86.58,0.4899,84.25,0.0742
-10.0,SC-CoT,Qwen2.5-7B-Instruct,2025/1/22,84.91,88.32,0.0,81.49,0.0
-11.0,PoT,gpt-4o,2025/1/22,84.15,93.1,4.2166,75.19,1.6087
-12.0,PoT,Qwen2.5-72B-Instruct,2025/1/22,83.77,92.34,0.7054,75.19,0.1645
+10.0,SC-CoT,Qwen2.5-7B-Instruct,2025/1/22,84.91,88.32,0.0,81.5,0.0
+11.0,PoT,gpt-4o,2025/1/22,84.15,93.1,4.2166,75.2,1.6087
+12.0,PoT,Qwen2.5-72B-Instruct,2025/1/22,83.77,92.34,0.7054,75.2,0.1645
 13.0,ReAct-Pro*,Llama-3.3-70B-Instruct,2025/1/22,83.39,87.64,10.1124,79.13,0.768
-14.0,CoT,Qwen2.5-7B-Instruct,2025/1/22,83.19,85.67,0.0,80.7,0.0
+14.0,CoT,Qwen2.5-7B-Instruct,2025/1/22,83.19,85.67,0.0,80.71,0.0
 15.0,SC-CoT,Doubao-lite-32k,2025/1/7,82.60,83.7,0.155,81.5,0.0347
 16.0,IO,gpt-4o,2025/1/22,82.00,88.4,3.3463,75.59,1.1453
-17.0,ReAct-Pro*,Doubao-lite-32k,2025/1/7,81.57,85.59,0.2512,77.55,0.0445
-18.0,ReAct-Pro*,Qwen2.5-72B-Instruct,2025/1/22,80.24,87.26,10.5479,73.22,0.3177
-19.0,ReAct-Pro*,Qwen2.5-7B-Instruct,2025/1/22,78.63,82.86,0.0,74.4,0.0
+17.0,ReAct-Pro*,Doubao-lite-32k,2025/1/7,81.58,85.6,0.2512,77.56,0.0445
+18.0,ReAct-Pro*,Qwen2.5-72B-Instruct,2025/1/22,80.25,87.26,10.5479,73.23,0.3177
+19.0,ReAct-Pro*,Qwen2.5-7B-Instruct,2025/1/22,78.64,82.87,0.0,74.41,0.0
 20.0,SC-CoT,gpt-3.5-turbo,2025/1/7,76.52,82.56,2.6285,70.47,0.5578
-21.0,PoT,Llama-3.3-70B-Instruct,2025/1/22,76.30,73.08,0.9736,79.52,0.1746
-22.0,PoT,Doubao-lite-32k,2025/1/7,75.63,79.6,0.0576,71.65,0.0147
+21.0,PoT,Llama-3.3-70B-Instruct,2025/1/22,76.31,73.09,0.9736,79.53,0.1746
+22.0,PoT,Doubao-lite-32k,2025/1/7,75.63,79.61,0.0576,71.65,0.0147
 23.0,IO,Doubao-lite-32k,2025/1/7,75.58,72.02,0.0354,79.13,0.0058
-24.0,CoT,gpt-3.5-turbo,2025/1/7,69.86,78.69,0.6788,61.02,0.0957
-25.0,ReAct-Pro*,gpt-3.5-turbo,2025/1/7,69.73,74.9,3.4633,64.56,0.4928
-26.0,PoT,gpt-3.5-turbo,2025/1/7,68.16,76.87,0.6902,59.44,0.1748
-27.0,CoT,Llama-3.1-8B-Instruct,2025/1/22,68.03,75.43,0.0,60.62,0.0
+24.0,CoT,gpt-3.5-turbo,2025/1/7,69.86,78.7,0.6788,61.02,0.0957
+25.0,ReAct-Pro*,gpt-3.5-turbo,2025/1/7,69.74,74.91,3.4633,64.57,0.4928
+26.0,PoT,gpt-3.5-turbo,2025/1/7,68.17,76.88,0.6902,59.45,0.1748
+27.0,CoT,Llama-3.1-8B-Instruct,2025/1/22,68.04,75.44,0.0,60.63,0.0
 28.0,IO,Qwen2.5-7B-Instruct,2025/1/22,67.99,57.24,0.0,78.74,0.0
-29.0,CoT,Internllm2_5-7B,2025/1/22,65.23,77.71,0.0,52.75,0.0
-30.0,SC-CoT,Llama-3.1-8B-Instruct,2025/1/22,64.17,75.2,0.0,53.14,0.0
+29.0,CoT,Internllm2_5-7B,2025/1/22,65.24,77.71,0.0,52.76,0.0
+30.0,SC-CoT,Llama-3.1-8B-Instruct,2025/1/22,64.18,75.21,0.0,53.15,0.0
 31.0,PoT,Qwen2.5-7B-Instruct,2025/1/22,63.47,58.83,0.0,68.11,0.0
-32.0,ReAct-Pro*,Llama-3.1-8B-Instruct,2025/1/22,61.64,67.77,0.0,55.51,0.0
-33.0,ReAct-Pro*,gpt-4o,2025/1/22,60.39,63.3,39.0751,57.48,2.304
+32.0,ReAct-Pro*,Llama-3.1-8B-Instruct,2025/1/22,61.65,67.78,0.0,55.51,0.0
+33.0,ReAct-Pro*,gpt-4o,2025/1/22,60.40,63.31,39.0751,57.48,2.304
 34.0,IO,Llama-3.1-8B-Instruct,2025/1/22,54.17,57.16,0.0,51.18,0.0
-35.0,CoT,Qwen2-1.5B-Instruct,2025/1/22,48.02,55.49,0.0,40.55,0.0
+35.0,CoT,Qwen2-1.5B-Instruct,2025/1/22,48.03,55.5,0.0,40.55,0.0
 36.0,SC-CoT,Internllm2_5-7B,2025/1/22,38.62,41.39,0.0,35.85,0.0
-37.0,IO,gpt-3.5-turbo,2025/1/7,38.40,37.83,0.3328,38.97,0.038
-38.0,PoT,Llama-3.1-8B-Instruct,2025/1/22,37.64,38.66,0.0,36.61,0.0
+37.0,IO,gpt-3.5-turbo,2025/1/7,38.41,37.83,0.3328,38.98,0.038
+38.0,PoT,Llama-3.1-8B-Instruct,2025/1/22,37.64,38.67,0.0,36.61,0.0
 39.0,PoT,Internllm2_5-7B,2025/1/22,37.41,38.21,0.0,36.61,0.0
 40.0,ReAct-Pro*,Internllm2_5-7B,2025/1/22,37.23,33.51,0.0,40.94,0.0
-41.0,CoT,Qwen2-0.5B-Instruct,2025/1/22,34.50,35.93,0.0,33.07,0.0
-42.0,IO,Internllm2_5-7B,2025/1/22,29.61,11.59,0.0,47.63,0.0
-43.0,ReAct-Pro*,Qwen2-1.5B-Instruct,2025/1/22,25.23,24.86,0.0,25.59,0.0
-44.0,PoT,Qwen2-1.5B-Instruct,2025/1/22,24.60,18.49,0.0,30.7,0.0
-45.0,IO,Qwen2-1.5B-Instruct,2025/1/22,22.90,16.67,0.0,29.13,0.0
-46.0,IO,Qwen2-0.5B-Instruct,2025/1/22,20.93,14.7,0.0,27.16,0.0
+41.0,CoT,Qwen2-0.5B-Instruct,2025/1/22,34.51,35.94,0.0,33.07,0.0
+42.0,IO,Internllm2_5-7B,2025/1/22,29.62,11.6,0.0,47.64,0.0
+43.0,ReAct-Pro*,Qwen2-1.5B-Instruct,2025/1/22,25.23,24.87,0.0,25.59,0.0
+44.0,PoT,Qwen2-1.5B-Instruct,2025/1/22,24.61,18.5,0.0,30.71,0.0
+45.0,IO,Qwen2-1.5B-Instruct,2025/1/22,22.91,16.68,0.0,29.13,0.0
+46.0,IO,Qwen2-0.5B-Instruct,2025/1/22,20.94,14.71,0.0,27.17,0.0
 47.0,SC-CoT,Qwen2-1.5B-Instruct,2025/1/22,17.92,5.53,0.0,30.31,0.0
-48.0,SC-CoT,Qwen2-0.5B-Instruct,2025/1/22,17.25,3.79,0.0,30.7,0.0
-49.0,ReAct-Pro*,Qwen2-0.5B-Instruct,2025/1/22,15.83,7.65,0.0,24.01,0.0
+48.0,SC-CoT,Qwen2-0.5B-Instruct,2025/1/22,17.25,3.79,0.0,30.71,0.0
+49.0,ReAct-Pro*,Qwen2-0.5B-Instruct,2025/1/22,15.84,7.66,0.0,24.02,0.0
 50.0,PoT,Qwen2-0.5B-Instruct,2025/1/22,13.47,9.62,0.0,17.32,0.0

src/record.csv

@@ -1,148 +1,148 @@
-Algorithm,dataset,llm,Score,Pass rate,X-shot,X-shot,Parameters,Nums,Total input tokens,Average input tokens,Total output tokens,Average output tokens,All tokens,Cost($),Eval Date,Note,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,gpt-3.5-turbo,37.83,99.92,8,few_shot,,1319,"546,990",415,"39,563",30,"586,553",0.3328,2025/1/7,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Doubao-lite-32k,72.02,99.92,8,few_shot,,1319,"617,377",468,"123,106",93,"740,483",0.0354,2025/1/7,0.2590 （元）,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,gpt-4o,88.4,100,8,few_shot,,1319,"542,416",411,"199,030",151,"741,446",3.3463,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Qwen2.5-72B-Instruct,86.58,100,8,few_shot,,1319,"555,340",421,"313,720",238,"869,060",0.4899,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Llama-3.3-70B-Instruct,92.26,100,8,few_shot,,1319,"583,916",443,"251,359",191,"835,275",0.4709,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Qwen2.5-7B-Instruct,57.24,100,8,few_shot,,1319,"596,229",452,"291,684",221,"887,913",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Llama-3.1-8B-Instruct,57.16,99.54,8,few_shot,,1319,"550,941",418,"1,194,488",906,"1,745,429",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Internllm2_5-7B,11.59,97.95,8,few_shot,,1319,"679,302",515,"434,426",329,"1,113,728",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Qwen2-1.5B-Instruct,16.67,100,8,few_shot,,1319,"568,530",431,"168,466",128,"736,996",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,gsm8k,Qwen2-0.5B-Instruct,14.7,100,8,few_shot,,1319,"568,116",431,"266,781",202,"834,897",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,gpt-3.5-turbo,74.9,99.39,8,few_shot,max_steps=10,1319,"6,506,164","4,933","140,122",106,"6,646,286",3.4633,2025/1/7,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Doubao-lite-32k,85.59,99.62,8,few_shot,max_steps=10,1319,"5,862,016","4,444","136,623",104,"5,998,639",0.2512,2025/1/7,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,gpt-4o,63.3,99.54,8,few_shot,max_steps=10,1319,"14,411,173","10,926","304,714",231,"14,715,887",39.0751,2025/1/22,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Qwen2.5-72B-Instruct,87.26,100,8,few_shot,max_steps=10,1319,"18,160,983","13,769","549,454",417,"18,710,437",10.5479,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Llama-3.3-70B-Instruct,87.64,99.92,,few_shot,max_steps=10,1319,"17,038,928","12,918","898,936",682,"17,937,864",10.1124,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Qwen2.5-7B-Instruct,82.86,100,8,few_shot,max_steps=10,1319,"14,355,752","10,884","495,162",375,"14,850,914",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Llama-3.1-8B-Instruct,67.77,98.55,8,few_shot,max_steps=10,1319,"21,044,978","15,955","1,790,789","1,358","22,835,767",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Internllm2_5-7B,33.51,97.95,,few_shot,max_steps=10,1319,"30,120,070","22,836","5,549,919","4,208","35,669,989",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Qwen2-1.5B-Instruct,24.86,80.21,8,few_shot,max_steps=10,1319,"9,133,603","6,925","694,398",526,"9,828,001",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,gsm8k,Qwen2-0.5B-Instruct,7.65,95.22,8,few_shot,max_steps=10,1319,"52,431,343","39,751","2,961,268","2,245","55,392,611",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,gpt-3.5-turbo,76.87,99.24,8,few_shot,,1319,"1,090,418",827,"96,662",73,"1,187,080",0.6902,2025/1/7,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Doubao-lite-32k,79.6,92.57,8,few_shot,,1319,"1,170,038",887,"118,017",89,"1,288,055",0.0576,2025/1/7,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,gpt-4o,93.1,99.77,8,few_shot,,1319,"1,101,672",835,"146,240",111,"1,247,912",4.2166,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Qwen2.5-72B-Instruct,92.34,99.39,8,few_shot,,1319,"1,106,682",839,"144,528",110,"1,251,210",0.7054,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Llama-3.3-70B-Instruct,73.08,79.6,8,few_shot,,1319,"1,126,025",854,"601,019",456,"1,727,044",0.9736,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Qwen2.5-7B-Instruct,58.83,70.5,8,few_shot,,1319,"1,145,390",868,"217,432",165,"1,362,822",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Llama-3.1-8B-Instruct,38.66,55.42,8,few_shot,,1319,"1,147,538",870,"243,573",185,"1,391,111",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Internllm2_5-7B,38.21,48.9,8,few_shot,,1319,"1,136,843",862,"188,106",143,"1,324,949",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Qwen2-1.5B-Instruct,18.49,31,8,few_shot,,1319,"1,151,528",873,"175,994",133,"1,327,522",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,gsm8k,Qwen2-0.5B-Instruct,9.62,16.9,8,few_shot,,1319,"1,151,528",873,"237,607",180,"1,389,135",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,gpt-3.5-turbo,78.69,100,8,few_shot,,1319,"953,242",723,"134,799",102,"1,088,041",0.6788,2025/1/7,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Doubao-lite-32k,89.31,100,8,few_shot,,1319,"1,042,095",790,"159,725",121,"1,201,820",0.0558,2025/1/7,0.4084635 （元）,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,gpt-4o,94.08,100,8,few_shot,,1319,"948,668",719,"216,498",164,"1,165,166",4.5367,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Qwen2.5-72B-Instruct,92.87,100,8,few_shot,,1319,"1,005,119",762,"271,133",206,"1,276,252",0.7195,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Llama-3.3-70B-Instruct,93.93,100,8,few_shot,,1319,"990,168",751,"228,497",173,"1,218,665",0.6870,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Qwen2.5-7B-Instruct,85.67,100,8,few_shot,,1319,"1,046,008",793,"244,797",186,"1,290,805",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Llama-3.1-8B-Instruct,75.43,99.92,8,few_shot,,1319,"990,168",751,"258,161",196,"1,248,329",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Internllm2_5-7B,77.71,99.69,8,few_shot,,1319,"968,163",734,"234,000",177,"1,202,163",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Qwen2-1.5B-Instruct,55.49,100,8,few_shot,,1319,"1,032,818",783,"185,707",141,"1,218,525",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,gsm8k,Qwen2-0.5B-Instruct,35.93,99.92,8,few_shot,,1319,"1,032,818",783,"190,641",145,"1,223,459",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,gpt-3.5-turbo,82.56,99.85,8,few_shot,"temperature=1, path_num=5",1319,"1,212,520",919,"1,348,177","1,022","2,560,697",2.6285,2025/1/7,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Doubao-lite-32k,83.7,99.70,8,few_shot,"temperature=1, path_num=5",1319,"1,230,019",933,"1,277,668",969,"2,507,687",0.1550,2025/1/7,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,gpt-4o,90.75,100,8,few_shot,"temperature=1, path_num=5",1319,"1,168,927",886,"2,132,044","1,616","3,300,971",24.2428,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Qwen2.5-72B-Instruct,90.67,100,8,few_shot,"temperature=1, path_num=5",1319,"5,292,383","4,012","2,273,254","1,723","7,565,637",4.2651,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Llama-3.3-70B-Instruct,95.45,100,8,few_shot,"temperature=1, path_num=5",1319,"5,406,763","4,099","2,579,233","1,955","7,985,996",4.5021,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Qwen2.5-7B-Instruct,88.32,99.84,8,few_shot,"temperature=1, path_num=5",1319,"5,668,252","4,297","2,505,566","1,900","8,173,818",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Llama-3.1-8B-Instruct,75.2,99.54,8,few_shot,"temperature=1, path_num=5",1319,"5,334,657","4,044","3,109,546","2,358","8,444,203",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Internllm2_5-7B,41.39,98.25,8,few_shot,"temperature=1, path_num=5",1319,"6,674,518","5,060","3,350,339","2,540","10,024,857",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Qwen2-1.5B-Instruct,5.53,86.73,8,few_shot,"temperature=1, path_num=5",1319,"5,844,218","4,431","3,117,550","2,364","8,961,768",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,gsm8k,Qwen2-0.5B-Instruct,3.79,94.84,8,few_shot,"temperature=1, path_num=5",1319,"6,529,832","4,951","4,003,983","3,036","10,533,815",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,gpt-3.5-turbo,38.97,100,0,zero_shot,,254,"25,701",101,"16,770",66,"42,471",0.0380,2025/1/7,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Doubao-lite-32k,79.13,100,0,zero_shot,,254,"33,058",130,"54,684",215,"87,742",0.0058,2025/1/7,0.0427（元）,,,,,,,,,,,,,,,,,,,
-IO,AQuA,gpt-4o,75.59,97.24,0,zero_shot,,254,"25,631",101,"108,121",426,"133,752",1.1453,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Qwen2.5-72B-Instruct,84.25,99.6,0,zero_shot,,254,"25,397",100,"106,207",418,"131,604",0.0742,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Llama-3.3-70B-Instruct,82.67,99.21,0,zero_shot,,254,"32,809",129,"108,758",428,"141,567",0.0798,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Qwen2.5-7B-Instruct,78.74,98.42,0,zero_shot,,254,"33,271",131,"104,500",411,"137,771",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Llama-3.1-8B-Instruct,51.18,98.81,0,zero_shot,,254,"26,459",104,"106,647",420,"133,106",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Internllm2_5-7B,47.63,90.94,0,zero_shot,,254,"50,232",198,"134,809",531,"185,041",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Qwen2-1.5B-Instruct,29.13,97.63,0,zero_shot,,254,"27,937",110,"43,110",170,"71,047",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-IO,AQuA,Qwen2-0.5B-Instruct,27.16,98.81,0,zero_shot,,254,"27,937",110,"82,478",325,"110,415",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,gpt-3.5-turbo,61.02,93.7,0,zero_shot,,254,"25,447",100,"55,346",218,"80,793",0.0957,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Doubao-lite-32k,82.67,97.24,0,zero_shot,,254,"27,978",110,"66,599",262,"94,577",0.0066,2025/1/7,0.0483 （元）,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,gpt-4o,82.67,98.03,0,zero_shot,,254,"25,123",99,"97,894",385,"123,017",1.0417,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Qwen2.5-72B-Instruct,86.22,99.21,0,zero_shot,,254,"25,143",99,"118,146",465,"143,289",0.0808,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Llama-3.3-70B-Instruct,83.46,98.42,0,zero_shot,,254,"32,555",128,"131,834",519,"164,389",0.0927,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Qwen2.5-7B-Instruct,80.7,99.6,0,zero_shot,,254,"33,017",130,"116,719",460,"149,736",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Llama-3.1-8B-Instruct,60.62,100,0,zero_shot,,254,"32,555",128,"111,880",440,"144,435",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Internllm2_5-7B,52.75,89.37,0,zero_shot,,254,"26,610",105,"100,910",397,"127,520",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Qwen2-1.5B-Instruct,40.55,98.81,0,zero_shot,,254,"30,477",120,"79,563",313,"110,040",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-CoT,AQuA,Qwen2-0.5B-Instruct,33.07,98.81,0,zero_shot,,254,"30,477",120,"86,862",342,"117,339",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,gpt-3.5-turbo,59.44,100,0,zero_shot,,254,"225,162",886,"41,492",163,"266,654",0.1748,2025/1/7,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,gpt-4o,75.19,100,0,zero_shot,,254,"222,717",877,"105,191",414,"327,908",1.6087,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Doubao-lite-32k,71.65,96.85,0,zero_shot,,254,"259,863","1,023","49,573",195,"309,436",0.0147,2025/1/7,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Qwen2.5-72B-Instruct,75.19,100,0,zero_shot,,254,"249,215",981,"42,549",168,"291,764",0.1645,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Llama-3.3-70B-Instruct,79.52,99.21,0,zero_shot,,254,"240,735",948,"69,064",272,"309,799",0.1746,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Qwen2.5-7B-Instruct,68.11,100,0,zero_shot,,254,"264,517","1,041","49,211",194,"313,728",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Llama-3.1-8B-Instruct,36.61,96.85,0,zero_shot,,254,"240,613",947,"50,301",198,"290,914",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Internllm2_5-7B,36.61,98.81,0,zero_shot,,254,"233,505",919,"68,457",270,"301,962",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Qwen2-1.5B-Instruct,30.7,96.45,0,zero_shot,,254,"246,560",971,"51,915",204,"298,475",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-PoT,AQuA,Qwen2-0.5B-Instruct,17.32,92.12,0,zero_shot,,254,"258,867","1,019","63,414",250,"322,281",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,gpt-3.5-turbo,70.47,98.82,0,zero_shot,"temperature=1, path_num=5",254,"70,157",276,"348,460","1,372","418,617",0.5578,2025/1/7,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Doubao-lite-32k,81.5,97.64,0,zero_shot,"temperature=1, path_num=5",254,"83,830",330,"382,016","1,504","465,846",0.0347,2025/1/7,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,gpt-4o,88.19,100,0,zero_shot,"temperature=1, path_num=5",254,"72,916",287,"605,895","2,385","678,811",6.2412,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Qwen2.5-72B-Instruct,85.82,98.42,0,zero_shot,"temperature=1, path_num=5",254,"241,149",949,"747,909","2,945","989,058",0.5576,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Llama-3.3-70B-Instruct,86.61,99.21,0,zero_shot,"temperature=1, path_num=5",254,"283,248","1,115","753,876","2,968","1,037,124",0.5847,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Qwen2.5-7B-Instruct,81.49,100,0,zero_shot,"temperature=1, path_num=5",254,"278,848","1,098","736,520","2,900","1,015,368",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Llama-3.1-8B-Instruct,53.14,96.06,0,zero_shot,"temperature=1, path_num=5",254,"372,968","1,468","668,378","2,631","1,041,346",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Internllm2_5-7B,35.85,98.8,0,zero_shot,"temperature=1, path_num=5",254,"530,701","2,089","709,687","2,794","1,240,388",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Qwen2-1.5B-Instruct,30.31,97.24,0,zero_shot,"temperature=1, path_num=5",254,"430,703","1,696","726,373","2,860","1,157,076",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-SC-CoT,AQuA,Qwen2-0.5B-Instruct,30.7,98.42,0,zero_shot,"temperature=1, path_num=5",254,"496,206","1,954","729,333","2,871","1,225,539",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,gpt-3.5-turbo,64.56,98.03,0,zero_shot,max_steps=10,254,"862,614","3,396","40,973",161,"903,587",0.4928,2025/1/7,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Doubao-lite-32k,77.55,96.06,0,zero_shot,max_steps=10,254,"977,890","3,850","54,951",216,"1,032,841",0.0445,2025/1/7,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,gpt-4o,57.48,97.24,0,zero_shot,max_steps=10,254,"615,589","2,424","76,507",301,"692,096",2.3040,2025/1/22,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Qwen2.5-72B-Instruct,73.22,100,0,zero_shot,max_steps=10,254,"441,765","1,739","121,838",480,"563,603",0.3177,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Llama-3.3-70B-Instruct,79.13,99.6,0,zero_shot,max_steps=10,254,"1,119,143","4,406","243,236",958,"1,362,379",0.7680,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Qwen2.5-7B-Instruct,74.4,99.21,0,zero_shot,max_steps=10,254,"564,165","2,221","131,679",518,"695,844",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Llama-3.1-8B-Instruct,55.51,96.85,0,zero_shot,max_steps=10,254,"3,764,723","14,822","576,098","2,268","4,340,821",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Internllm2_5-7B,40.94,96.85,0,zero_shot,max_steps=10,254,"3,592,039","14,142","836,762","3,294","4,428,801",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Qwen2-1.5B-Instruct,25.59,96.06,0,zero_shot,max_steps=10,254,"4,555,858","17,936","516,146","2,032","5,072,004",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-ReAct-Pro*,AQuA,Qwen2-0.5B-Instruct,24.01,96.85,0,zero_shot,max_steps=10,254,6344167,"24,977",825920,"3,252","7,170,087",0.0000,2025/1/22,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
-,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+Algorithm,Dataset,Eval Date,LLM,Score,Pass rate,X-shot,Parameters,Samples,Total input tokens,Average input tokens,Total output tokens,Average output tokens,All tokens,Cost($),Note,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/7,gpt-3.5-turbo,37.83,99.92,8,,1319,"546,990",415,"39,563",30,"586,553",0.3328,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/7,Doubao-lite-32k,72.02,99.92,8,,1319,"617,377",468,"123,106",93,"740,483",0.0354,0.2590 （元）,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,gpt-4o,88.4,100,8,,1319,"542,416",411,"199,030",151,"741,446",3.3463,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Qwen2.5-72B-Instruct,86.58,100,8,,1319,"555,340",421,"313,720",238,"869,060",0.4899,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Llama-3.3-70B-Instruct,92.27,100,8,,1319,"583,916",443,"251,359",191,"835,275",0.4709,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Qwen2.5-7B-Instruct,57.24,100,8,,1319,"596,229",452,"291,684",221,"887,913",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Llama-3.1-8B-Instruct,57.16,99.55,8,,1319,"550,941",418,"1,194,488",906,"1,745,429",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Internllm2_5-7B,11.6,97.95,8,,1319,"679,302",515,"434,426",329,"1,113,728",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Qwen2-1.5B-Instruct,16.68,100,8,,1319,"568,530",431,"168,466",128,"736,996",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,gsm8k,2025/1/22,Qwen2-0.5B-Instruct,14.71,100,8,,1319,"568,116",431,"266,781",202,"834,897",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/7,gpt-3.5-turbo,74.91,99.39,8,max_steps=10,1319,"6,506,164","4,933","140,122",106,"6,646,286",3.4633,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/7,Doubao-lite-32k,85.6,99.62,8,max_steps=10,1319,"5,862,016","4,444","136,623",104,"5,998,639",0.2512,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,gpt-4o,63.31,99.55,8,max_steps=10,1319,"14,411,173","10,926","304,714",231,"14,715,887",39.0751,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Qwen2.5-72B-Instruct,87.26,100,8,max_steps=10,1319,"18,160,983","13,769","549,454",417,"18,710,437",10.5479,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Llama-3.3-70B-Instruct,87.64,99.92,8,max_steps=10,1319,"17,038,928","12,918","898,936",682,"17,937,864",10.1124,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Qwen2.5-7B-Instruct,82.87,100,8,max_steps=10,1319,"14,355,752","10,884","495,162",375,"14,850,914",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Llama-3.1-8B-Instruct,67.78,98.56,8,max_steps=10,1319,"21,044,978","15,955","1,790,789","1,358","22,835,767",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Internllm2_5-7B,33.51,97.95,8,max_steps=10,1319,"30,120,070","22,836","5,549,919","4,208","35,669,989",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Qwen2-1.5B-Instruct,24.87,80.21,8,max_steps=10,1319,"9,133,603","6,925","694,398",526,"9,828,001",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,gsm8k,2025/1/22,Qwen2-0.5B-Instruct,7.66,95.22,8,max_steps=10,1319,"52,431,343","39,751","2,961,268","2,245","55,392,611",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/7,gpt-3.5-turbo,76.88,99.24,8,,1319,"1,090,418",827,"96,662",73,"1,187,080",0.6902,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/7,Doubao-lite-32k,79.61,92.57,8,,1319,"1,170,038",887,"118,017",89,"1,288,055",0.0576,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,gpt-4o,93.1,99.77,8,,1319,"1,101,672",835,"146,240",111,"1,247,912",4.2166,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Qwen2.5-72B-Instruct,92.34,99.39,8,,1319,"1,106,682",839,"144,528",110,"1,251,210",0.7054,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Llama-3.3-70B-Instruct,73.09,79.61,8,,1319,"1,126,025",854,"601,019",456,"1,727,044",0.9736,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Qwen2.5-7B-Instruct,58.83,70.51,8,,1319,"1,145,390",868,"217,432",165,"1,362,822",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Llama-3.1-8B-Instruct,38.67,55.42,8,,1319,"1,147,538",870,"243,573",185,"1,391,111",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Internllm2_5-7B,38.21,48.9,8,,1319,"1,136,843",862,"188,106",143,"1,324,949",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Qwen2-1.5B-Instruct,18.5,31.01,8,,1319,"1,151,528",873,"175,994",133,"1,327,522",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,gsm8k,2025/1/22,Qwen2-0.5B-Instruct,9.62,16.9,8,,1319,"1,151,528",873,"237,607",180,"1,389,135",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/7,gpt-3.5-turbo,78.7,100,8,,1319,"953,242",723,"134,799",102,"1,088,041",0.6788,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/7,Doubao-lite-32k,89.31,100,8,,1319,"1,042,095",790,"159,725",121,"1,201,820",0.0558,0.4084635 （元）,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,gpt-4o,94.09,100,8,,1319,"948,668",719,"216,498",164,"1,165,166",4.5367,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Qwen2.5-72B-Instruct,92.87,100,8,,1319,"1,005,119",762,"271,133",206,"1,276,252",0.7195,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Llama-3.3-70B-Instruct,93.93,100,8,,1319,"990,168",751,"228,497",173,"1,218,665",0.6870,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Qwen2.5-7B-Instruct,85.67,100,8,,1319,"1,046,008",793,"244,797",186,"1,290,805",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Llama-3.1-8B-Instruct,75.44,99.92,8,,1319,"990,168",751,"258,161",196,"1,248,329",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Internllm2_5-7B,77.71,99.7,8,,1319,"968,163",734,"234,000",177,"1,202,163",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Qwen2-1.5B-Instruct,55.5,100,8,,1319,"1,032,818",783,"185,707",141,"1,218,525",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,gsm8k,2025/1/22,Qwen2-0.5B-Instruct,35.94,99.92,8,,1319,"1,032,818",783,"190,641",145,"1,223,459",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/7,gpt-3.5-turbo,82.56,99.85,8,"temperature=1, path_num=5",1319,"1,212,520",919,"1,348,177","1,022","2,560,697",2.6285,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/7,Doubao-lite-32k,83.7,99.7,8,"temperature=1, path_num=5",1319,"1,230,019",933,"1,277,668",969,"2,507,687",0.1550,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,gpt-4o,90.75,100,8,"temperature=1, path_num=5",1319,"1,168,927",886,"2,132,044","1,616","3,300,971",24.2428,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Qwen2.5-72B-Instruct,90.67,100,8,"temperature=1, path_num=5",1319,"5,292,383","4,012","2,273,254","1,723","7,565,637",4.2651,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Llama-3.3-70B-Instruct,95.45,100,8,"temperature=1, path_num=5",1319,"5,406,763","4,099","2,579,233","1,955","7,985,996",4.5021,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Qwen2.5-7B-Instruct,88.32,99.85,8,"temperature=1, path_num=5",1319,"5,668,252","4,297","2,505,566","1,900","8,173,818",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Llama-3.1-8B-Instruct,75.21,99.55,8,"temperature=1, path_num=5",1319,"5,334,657","4,044","3,109,546","2,358","8,444,203",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Internllm2_5-7B,41.39,98.26,8,"temperature=1, path_num=5",1319,"6,674,518","5,060","3,350,339","2,540","10,024,857",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Qwen2-1.5B-Instruct,5.53,86.73,8,"temperature=1, path_num=5",1319,"5,844,218","4,431","3,117,550","2,364","8,961,768",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,gsm8k,2025/1/22,Qwen2-0.5B-Instruct,3.79,94.84,8,"temperature=1, path_num=5",1319,"6,529,832","4,951","4,003,983","3,036","10,533,815",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/7,gpt-3.5-turbo,38.98,100,0,,254,"25,701",101,"16,770",66,"42,471",0.0380,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/7,Doubao-lite-32k,79.13,100,0,,254,"33,058",130,"54,684",215,"87,742",0.0058,0.0427（元）,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,gpt-4o,75.59,97.24,0,,254,"25,631",101,"108,121",426,"133,752",1.1453,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Qwen2.5-72B-Instruct,84.25,99.61,0,,254,"25,397",100,"106,207",418,"131,604",0.0742,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Llama-3.3-70B-Instruct,82.68,99.21,0,,254,"32,809",129,"108,758",428,"141,567",0.0798,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Qwen2.5-7B-Instruct,78.74,98.43,0,,254,"33,271",131,"104,500",411,"137,771",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Llama-3.1-8B-Instruct,51.18,98.82,0,,254,"26,459",104,"106,647",420,"133,106",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Internllm2_5-7B,47.64,90.94,0,,254,"50,232",198,"134,809",531,"185,041",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Qwen2-1.5B-Instruct,29.13,97.64,0,,254,"27,937",110,"43,110",170,"71,047",0.0000,,,,,,,,,,,,,,,,,,,,
+IO,AQuA,2025/1/22,Qwen2-0.5B-Instruct,27.17,98.82,0,,254,"27,937",110,"82,478",325,"110,415",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,gpt-3.5-turbo,61.02,93.7,0,,254,"25,447",100,"55,346",218,"80,793",0.0957,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/7,Doubao-lite-32k,82.68,97.24,0,,254,"27,978",110,"66,599",262,"94,577",0.0066,0.0483 （元）,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,gpt-4o,82.68,98.03,0,,254,"25,123",99,"97,894",385,"123,017",1.0417,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Qwen2.5-72B-Instruct,86.22,99.21,0,,254,"25,143",99,"118,146",465,"143,289",0.0808,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Llama-3.3-70B-Instruct,83.46,98.43,0,,254,"32,555",128,"131,834",519,"164,389",0.0927,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Qwen2.5-7B-Instruct,80.71,99.61,0,,254,"33,017",130,"116,719",460,"149,736",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Llama-3.1-8B-Instruct,60.63,100,0,,254,"32,555",128,"111,880",440,"144,435",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Internllm2_5-7B,52.76,89.37,0,,254,"26,610",105,"100,910",397,"127,520",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Qwen2-1.5B-Instruct,40.55,98.82,0,,254,"30,477",120,"79,563",313,"110,040",0.0000,,,,,,,,,,,,,,,,,,,,
+CoT,AQuA,2025/1/22,Qwen2-0.5B-Instruct,33.07,98.82,0,,254,"30,477",120,"86,862",342,"117,339",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/7,gpt-3.5-turbo,59.45,100,0,,254,"225,162",886,"41,492",163,"266,654",0.1748,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/7,Doubao-lite-32k,71.65,96.85,0,,254,"259,863","1,023","49,573",195,"309,436",0.0147,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,gpt-4o,75.2,100,0,,254,"222,717",877,"105,191",414,"327,908",1.6087,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Qwen2.5-72B-Instruct,75.2,100,0,,254,"249,215",981,"42,549",168,"291,764",0.1645,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Llama-3.3-70B-Instruct,79.53,99.21,0,,254,"240,735",948,"69,064",272,"309,799",0.1746,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Qwen2.5-7B-Instruct,68.11,100,0,,254,"264,517","1,041","49,211",194,"313,728",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Llama-3.1-8B-Instruct,36.61,96.85,0,,254,"240,613",947,"50,301",198,"290,914",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Internllm2_5-7B,36.61,98.82,0,,254,"233,505",919,"68,457",270,"301,962",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Qwen2-1.5B-Instruct,30.71,96.46,0,,254,"246,560",971,"51,915",204,"298,475",0.0000,,,,,,,,,,,,,,,,,,,,
+PoT,AQuA,2025/1/22,Qwen2-0.5B-Instruct,17.32,92.13,0,,254,"258,867","1,019","63,414",250,"322,281",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/7,gpt-3.5-turbo,70.47,98.82,0,"temperature=1, path_num=5",254,"70,157",276,"348,460","1,372","418,617",0.5578,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/7,Doubao-lite-32k,81.5,97.64,0,"temperature=1, path_num=5",254,"83,830",330,"382,016","1,504","465,846",0.0347,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,gpt-4o,88.19,100,0,"temperature=1, path_num=5",254,"72,916",287,"605,895","2,385","678,811",6.2412,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Qwen2.5-72B-Instruct,85.83,98.43,0,"temperature=1, path_num=5",254,"241,149",949,"747,909","2,945","989,058",0.5576,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Llama-3.3-70B-Instruct,86.61,99.21,0,"temperature=1, path_num=5",254,"283,248","1,115","753,876","2,968","1,037,124",0.5847,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Qwen2.5-7B-Instruct,81.5,100,0,"temperature=1, path_num=5",254,"278,848","1,098","736,520","2,900","1,015,368",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Llama-3.1-8B-Instruct,53.15,96.06,0,"temperature=1, path_num=5",254,"372,968","1,468","668,378","2,631","1,041,346",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Internllm2_5-7B,35.85,98.8,0,"temperature=1, path_num=5",254,"530,701","2,089","709,687","2,794","1,240,388",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Qwen2-1.5B-Instruct,30.31,97.24,0,"temperature=1, path_num=5",254,"430,703","1,696","726,373","2,860","1,157,076",0.0000,,,,,,,,,,,,,,,,,,,,
+SC-CoT,AQuA,2025/1/22,Qwen2-0.5B-Instruct,30.71,98.43,0,"temperature=1, path_num=5",254,"496,206","1,954","729,333","2,871","1,225,539",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/7,gpt-3.5-turbo,64.57,98.03,0,max_steps=10,254,"862,614","3,396","40,973",161,"903,587",0.4928,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/7,Doubao-lite-32k,77.56,96.06,0,max_steps=10,254,"977,890","3,850","54,951",216,"1,032,841",0.0445,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,gpt-4o,57.48,97.24,0,max_steps=10,254,"615,589","2,424","76,507",301,"692,096",2.3040,"think-action 单独返回,prompt v1",,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Qwen2.5-72B-Instruct,73.23,100,0,max_steps=10,254,"441,765","1,739","121,838",480,"563,603",0.3177,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Llama-3.3-70B-Instruct,79.13,99.61,0,max_steps=10,254,"1,119,143","4,406","243,236",958,"1,362,379",0.7680,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Qwen2.5-7B-Instruct,74.41,99.21,0,max_steps=10,254,"564,165","2,221","131,679",518,"695,844",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Llama-3.1-8B-Instruct,55.51,96.85,0,max_steps=10,254,"3,764,723","14,822","576,098","2,268","4,340,821",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Internllm2_5-7B,40.94,96.85,0,max_steps=10,254,"3,592,039","14,142","836,762","3,294","4,428,801",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Qwen2-1.5B-Instruct,25.59,96.06,0,max_steps=10,254,"4,555,858","17,936","516,146","2,032","5,072,004",0.0000,,,,,,,,,,,,,,,,,,,,
+ReAct-Pro*,AQuA,2025/1/22,Qwen2-0.5B-Instruct,24.02,96.85,0,max_steps=10,254,6344167,"24,977",825920,"3,252","7,170,087",0.0000,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,