Upload results.html

results.html

@@ -0,0 +1,732 @@
+<style type="text/css">
+#T_a7af5 td {
+  overflow-wrap: break-word;
+  max-width: 1px;
+}
+#T_a7af5 .col_heading {
+  width: 25.0%;
+}
+#T_a7af5_row15_col0, #T_a7af5_row118_col1 {
+  background-color: #f7cbe4;
+  color: #000000;
+}
+#T_a7af5_row15_col1, #T_a7af5_row31_col3 {
+  background-color: #f9eff4;
+  color: #000000;
+}
+#T_a7af5_row15_col2, #T_a7af5_row58_col3, #T_a7af5_row109_col0 {
+  background-color: #f4bfdf;
+  color: #000000;
+}
+#T_a7af5_row15_col3, #T_a7af5_row28_col2, #T_a7af5_row46_col2, #T_a7af5_row85_col0, #T_a7af5_row107_col3 {
+  background-color: #f6c7e3;
+  color: #000000;
+}
+#T_a7af5_row19_col0 {
+  background-color: #a9d874;
+  color: #000000;
+}
+#T_a7af5_row19_col1 {
+  background-color: #549825;
+  color: #f1f1f1;
+}
+#T_a7af5_row19_col2, #T_a7af5_row70_col0, #T_a7af5_row115_col0 {
+  background-color: #f7f7f6;
+  color: #000000;
+}
+#T_a7af5_row19_col3 {
+  background-color: #f1f6ea;
+  color: #000000;
+}
+#T_a7af5_row22_col0 {
+  background-color: #f5f7f3;
+  color: #000000;
+}
+#T_a7af5_row22_col1 {
+  background-color: #edf6df;
+  color: #000000;
+}
+#T_a7af5_row22_col2, #T_a7af5_row22_col3, #T_a7af5_row37_col2, #T_a7af5_row70_col1 {
+  background-color: #f4f7f0;
+  color: #000000;
+}
+#T_a7af5_row25_col0, #T_a7af5_row100_col2, #T_a7af5_row145_col1 {
+  background-color: #eeabd2;
+  color: #000000;
+}
+#T_a7af5_row25_col1 {
+  background-color: #eff6e4;
+  color: #000000;
+}
+#T_a7af5_row25_col2, #T_a7af5_row40_col2 {
+  background-color: #df7cb1;
+  color: #f1f1f1;
+}
+#T_a7af5_row25_col3 {
+  background-color: #fbd9ec;
+  color: #000000;
+}
+#T_a7af5_row28_col0, #T_a7af5_row130_col0 {
+  background-color: #fbe7f2;
+  color: #000000;
+}
+#T_a7af5_row28_col1, #T_a7af5_row73_col1 {
+  background-color: #ecf6de;
+  color: #000000;
+}
+#T_a7af5_row28_col3 {
+  background-color: #f2badc;
+  color: #000000;
+}
+#T_a7af5_row31_col0, #T_a7af5_row105_col3 {
+  background-color: #f9f1f5;
+  color: #000000;
+}
+#T_a7af5_row31_col1, #T_a7af5_row37_col1 {
+  background-color: #e8f5d5;
+  color: #000000;
+}
+#T_a7af5_row31_col2, #T_a7af5_row40_col1 {
+  background-color: #f9eef4;
+  color: #000000;
+}
+#T_a7af5_row34_col0, #T_a7af5_row43_col0, #T_a7af5_row124_col1 {
+  background-color: #d24c97;
+  color: #f1f1f1;
+}
+#T_a7af5_row34_col1 {
+  background-color: #faeaf2;
+  color: #000000;
+}
+#T_a7af5_row34_col2, #T_a7af5_row67_col3 {
+  background-color: #e283b7;
+  color: #f1f1f1;
+}
+#T_a7af5_row34_col3 {
+  background-color: #fbe6f1;
+  color: #000000;
+}
+#T_a7af5_row37_col0, #T_a7af5_row49_col0 {
+  background-color: #f7f6f7;
+  color: #000000;
+}
+#T_a7af5_row37_col3, #T_a7af5_row46_col3, #T_a7af5_row52_col3 {
+  background-color: #f8f3f6;
+  color: #000000;
+}
+#T_a7af5_row40_col0 {
+  background-color: #e388ba;
+  color: #f1f1f1;
+}
+#T_a7af5_row40_col3 {
+  background-color: #eeadd4;
+  color: #000000;
+}
+#T_a7af5_row43_col1 {
+  background-color: #f6c9e3;
+  color: #000000;
+}
+#T_a7af5_row43_col2, #T_a7af5_row67_col2, #T_a7af5_row79_col1 {
+  background-color: #cf4191;
+  color: #f1f1f1;
+}
+#T_a7af5_row43_col3 {
+  background-color: #d34f99;
+  color: #f1f1f1;
+}
+#T_a7af5_row46_col0 {
+  background-color: #fde2f0;
+  color: #000000;
+}
+#T_a7af5_row46_col1 {
+  background-color: #bbe28a;
+  color: #000000;
+}
+#T_a7af5_row49_col1 {
+  background-color: #e9f5d6;
+  color: #000000;
+}
+#T_a7af5_row49_col2, #T_a7af5_row67_col1, #T_a7af5_row148_col0 {
+  background-color: #ea9fca;
+  color: #000000;
+}
+#T_a7af5_row49_col3 {
+  background-color: #f0b2d7;
+  color: #000000;
+}
+#T_a7af5_row52_col0, #T_a7af5_row142_col0 {
+  background-color: #f6f7f5;
+  color: #000000;
+}
+#T_a7af5_row52_col1 {
+  background-color: #c0e593;
+  color: #000000;
+}
+#T_a7af5_row52_col2, #T_a7af5_row58_col1, #T_a7af5_row64_col1, #T_a7af5_row109_col2 {
+  background-color: #fce5f1;
+  color: #000000;
+}
+#T_a7af5_row55_col0, #T_a7af5_row90_col1 {
+  background-color: #f5c6e2;
+  color: #000000;
+}
+#T_a7af5_row55_col1 {
+  background-color: #fad6ea;
+  color: #000000;
+}
+#T_a7af5_row55_col2 {
+  background-color: #f8cee6;
+  color: #000000;
+}
+#T_a7af5_row55_col3 {
+  background-color: #c82884;
+  color: #f1f1f1;
+}
+#T_a7af5_row58_col0, #T_a7af5_row121_col1 {
+  background-color: #e897c4;
+  color: #000000;
+}
+#T_a7af5_row58_col2, #T_a7af5_row79_col0, #T_a7af5_row107_col0 {
+  background-color: #e07eb3;
+  color: #f1f1f1;
+}
+#T_a7af5_row61_col0 {
+  background-color: #eba3cd;
+  color: #000000;
+}
+#T_a7af5_row61_col1, #T_a7af5_row88_col0, #T_a7af5_row88_col1, #T_a7af5_row88_col2, #T_a7af5_row88_col3, #T_a7af5_row109_col3 {
+  background-color: #f8f4f6;
+  color: #000000;
+}
+#T_a7af5_row61_col2, #T_a7af5_row136_col0 {
+  background-color: #dc70aa;
+  color: #f1f1f1;
+}
+#T_a7af5_row61_col3 {
+  background-color: #d861a2;
+  color: #f1f1f1;
+}
+#T_a7af5_row64_col0, #T_a7af5_row145_col3 {
+  background-color: #e181b5;
+  color: #f1f1f1;
+}
+#T_a7af5_row64_col2, #T_a7af5_row94_col3, #T_a7af5_row136_col3 {
+  background-color: #e48bbc;
+  color: #f1f1f1;
+}
+#T_a7af5_row64_col3, #T_a7af5_row138_col3, #T_a7af5_row148_col2 {
+  background-color: #f9d1e8;
+  color: #000000;
+}
+#T_a7af5_row67_col0, #T_a7af5_row76_col1 {
+  background-color: #cc368b;
+  color: #f1f1f1;
+}
+#T_a7af5_row70_col2, #T_a7af5_row73_col0 {
+  background-color: #f0f6e7;
+  color: #000000;
+}
+#T_a7af5_row70_col3, #T_a7af5_row73_col3 {
+  background-color: #f8f2f5;
+  color: #000000;
+}
+#T_a7af5_row73_col2 {
+  background-color: #f3f6ed;
+  color: #000000;
+}
+#T_a7af5_row76_col0, #T_a7af5_row133_col0 {
+  background-color: #b51370;
+  color: #f1f1f1;
+}
+#T_a7af5_row76_col2, #T_a7af5_row97_col2, #T_a7af5_row145_col0 {
+  background-color: #e590bf;
+  color: #f1f1f1;
+}
+#T_a7af5_row76_col3 {
+  background-color: #e692c1;
+  color: #000000;
+}
+#T_a7af5_row79_col2 {
+  background-color: #e286b8;
+  color: #f1f1f1;
+}
+#T_a7af5_row79_col3 {
+  background-color: #c72482;
+  color: #f1f1f1;
+}
+#T_a7af5_row82_col0 {
+  background-color: #d65a9f;
+  color: #f1f1f1;
+}
+#T_a7af5_row82_col1, #T_a7af5_row82_col3, #T_a7af5_row136_col2 {
+  background-color: #c92b86;
+  color: #f1f1f1;
+}
+#T_a7af5_row82_col2 {
+  background-color: #d14895;
+  color: #f1f1f1;
+}
+#T_a7af5_row85_col1, #T_a7af5_row94_col1 {
+  background-color: #f3bdde;
+  color: #000000;
+}
+#T_a7af5_row85_col2, #T_a7af5_row100_col1 {
+  background-color: #f5c2e0;
+  color: #000000;
+}
+#T_a7af5_row85_col3, #T_a7af5_row100_col3 {
+  background-color: #f1b7da;
+  color: #000000;
+}
+#T_a7af5_row90_col0, #T_a7af5_row105_col0, #T_a7af5_row136_col1 {
+  background-color: #f1b5d9;
+  color: #000000;
+}
+#T_a7af5_row90_col2 {
+  background-color: #e89ac6;
+  color: #000000;
+}
+#T_a7af5_row90_col3, #T_a7af5_row107_col2 {
+  background-color: #eda8d1;
+  color: #000000;
+}
+#T_a7af5_row94_col0, #T_a7af5_row127_col0 {
+  background-color: #eba1cb;
+  color: #000000;
+}
+#T_a7af5_row94_col2, #T_a7af5_row145_col2 {
+  background-color: #e58dbe;
+  color: #f1f1f1;
+}
+#T_a7af5_row97_col0, #T_a7af5_row107_col1 {
+  background-color: #f3bcdd;
+  color: #000000;
+}
+#T_a7af5_row97_col1 {
+  background-color: #f7cce5;
+  color: #000000;
+}
+#T_a7af5_row97_col3, #T_a7af5_row103_col2 {
+  background-color: #eca6cf;
+  color: #000000;
+}
+#T_a7af5_row100_col0 {
+  background-color: #efb0d6;
+  color: #000000;
+}
+#T_a7af5_row103_col0 {
+  background-color: #db6ca8;
+  color: #f1f1f1;
+}
+#T_a7af5_row103_col1 {
+  background-color: #e795c3;
+  color: #000000;
+}
+#T_a7af5_row103_col3, #T_a7af5_row138_col0 {
+  background-color: #f5c4e1;
+  color: #000000;
+}
+#T_a7af5_row105_col1 {
+  background-color: #fbd8eb;
+  color: #000000;
+}
+#T_a7af5_row105_col2, #T_a7af5_row127_col1 {
+  background-color: #fce4f0;
+  color: #000000;
+}
+#T_a7af5_row109_col1 {
+  background-color: #fbe9f2;
+  color: #000000;
+}
+#T_a7af5_row111_col0 {
+  background-color: #e99cc8;
+  color: #000000;
+}
+#T_a7af5_row111_col1, #T_a7af5_row138_col1 {
+  background-color: #fcdbed;
+  color: #000000;
+}
+#T_a7af5_row111_col2, #T_a7af5_row111_col3, #T_a7af5_row115_col2, #T_a7af5_row115_col3, #T_a7af5_row118_col2, #T_a7af5_row118_col3, #T_a7af5_row121_col2, #T_a7af5_row121_col3, #T_a7af5_row124_col2, #T_a7af5_row124_col3, #T_a7af5_row127_col2, #T_a7af5_row127_col3, #T_a7af5_row130_col2, #T_a7af5_row130_col3, #T_a7af5_row133_col2, #T_a7af5_row133_col3 {
+  background-color: #8e0152;
+  color: #f1f1f1;
+}
+#T_a7af5_row115_col1 {
+  background-color: #ddf1c1;
+  color: #000000;
+}
+#T_a7af5_row118_col0 {
+  background-color: #d4539b;
+  color: #f1f1f1;
+}
+#T_a7af5_row121_col0 {
+  background-color: #ca2f88;
+  color: #f1f1f1;
+}
+#T_a7af5_row124_col0 {
+  background-color: #b1116d;
+  color: #f1f1f1;
+}
+#T_a7af5_row130_col1 {
+  background-color: #d0ecad;
+  color: #000000;
+}
+#T_a7af5_row133_col1 {
+  background-color: #cb3289;
+  color: #f1f1f1;
+}
+#T_a7af5_row138_col2 {
+  background-color: #f8d0e7;
+  color: #000000;
+}
+#T_a7af5_row142_col1 {
+  background-color: #f3f7ef;
+  color: #000000;
+}
+#T_a7af5_row142_col2, #T_a7af5_row142_col3 {
+  background-color: #f8f5f6;
+  color: #000000;
+}
+#T_a7af5_row148_col1 {
+  background-color: #fad4e9;
+  color: #000000;
+}
+#T_a7af5_row148_col3 {
+  background-color: #fcdded;
+  color: #000000;
+}
+</style>
+<table id="T_a7af5">
+  <thead>
+    <tr>
+      <th class="blank level0" >&nbsp;</th>
+      <th id="T_a7af5_level0_col0" class="col_heading level0 col0" >Spestly/Atlas-Pro-1.5B-Preview</th>
+      <th id="T_a7af5_level0_col1" class="col_heading level0 col1" >Spestly/Atlas-Pro-7B-Preview</th>
+      <th id="T_a7af5_level0_col2" class="col_heading level0 col2" >deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B</th>
+      <th id="T_a7af5_level0_col3" class="col_heading level0 col3" >deepseek-ai/DeepSeek-R1-Distill-Qwen-7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th id="T_a7af5_level0_row15" class="row_heading level0 row15" >bbh.acc_norm</th>
+      <td id="T_a7af5_row15_col0" class="data row15 col0" >0.348030</td>
+      <td id="T_a7af5_row15_col1" class="data row15 col1" >0.465891</td>
+      <td id="T_a7af5_row15_col2" class="data row15 col2" >0.321298</td>
+      <td id="T_a7af5_row15_col3" class="data row15 col3" >0.341087</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row19" class="row_heading level0 row19" >bbh_boolean_expressions.acc_norm</th>
+      <td id="T_a7af5_row19_col0" class="data row19 col0" >0.724000</td>
+      <td id="T_a7af5_row19_col1" class="data row19 col1" >0.884000</td>
+      <td id="T_a7af5_row19_col2" class="data row19 col2" >0.500000</td>
+      <td id="T_a7af5_row19_col3" class="data row19 col3" >0.532000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row22" class="row_heading level0 row22" >bbh_causal_judgement.acc_norm</th>
+      <td id="T_a7af5_row22_col0" class="data row22 col0" >0.508021</td>
+      <td id="T_a7af5_row22_col1" class="data row22 col1" >0.561497</td>
+      <td id="T_a7af5_row22_col2" class="data row22 col2" >0.518717</td>
+      <td id="T_a7af5_row22_col3" class="data row22 col3" >0.518717</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row25" class="row_heading level0 row25" >bbh_date_understanding.acc_norm</th>
+      <td id="T_a7af5_row25_col0" class="data row25 col0" >0.284000</td>
+      <td id="T_a7af5_row25_col1" class="data row25 col1" >0.548000</td>
+      <td id="T_a7af5_row25_col2" class="data row25 col2" >0.208000</td>
+      <td id="T_a7af5_row25_col3" class="data row25 col3" >0.384000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row28" class="row_heading level0 row28" >bbh_disambiguation_qa.acc_norm</th>
+      <td id="T_a7af5_row28_col0" class="data row28 col0" >0.432000</td>
+      <td id="T_a7af5_row28_col1" class="data row28 col1" >0.564000</td>
+      <td id="T_a7af5_row28_col2" class="data row28 col2" >0.340000</td>
+      <td id="T_a7af5_row28_col3" class="data row28 col3" >0.312000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row31" class="row_heading level0 row31" >bbh_formal_fallacies.acc_norm</th>
+      <td id="T_a7af5_row31_col0" class="data row31 col0" >0.476000</td>
+      <td id="T_a7af5_row31_col1" class="data row31 col1" >0.588000</td>
+      <td id="T_a7af5_row31_col2" class="data row31 col2" >0.464000</td>
+      <td id="T_a7af5_row31_col3" class="data row31 col3" >0.468000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row34" class="row_heading level0 row34" >bbh_geometric_shapes.acc_norm</th>
+      <td id="T_a7af5_row34_col0" class="data row34 col0" >0.156000</td>
+      <td id="T_a7af5_row34_col1" class="data row34 col1" >0.444000</td>
+      <td id="T_a7af5_row34_col2" class="data row34 col2" >0.220000</td>
+      <td id="T_a7af5_row34_col3" class="data row34 col3" >0.428000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row37" class="row_heading level0 row37" >bbh_hyperbaton.acc_norm</th>
+      <td id="T_a7af5_row37_col0" class="data row37 col0" >0.496000</td>
+      <td id="T_a7af5_row37_col1" class="data row37 col1" >0.588000</td>
+      <td id="T_a7af5_row37_col2" class="data row37 col2" >0.516000</td>
+      <td id="T_a7af5_row37_col3" class="data row37 col3" >0.484000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row40" class="row_heading level0 row40" >bbh_logical_deduction_five_objects.acc_norm</th>
+      <td id="T_a7af5_row40_col0" class="data row40 col0" >0.228000</td>
+      <td id="T_a7af5_row40_col1" class="data row40 col1" >0.464000</td>
+      <td id="T_a7af5_row40_col2" class="data row40 col2" >0.208000</td>
+      <td id="T_a7af5_row40_col3" class="data row40 col3" >0.288000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row43" class="row_heading level0 row43" >bbh_logical_deduction_seven_objects.acc_norm</th>
+      <td id="T_a7af5_row43_col0" class="data row43 col0" >0.156000</td>
+      <td id="T_a7af5_row43_col1" class="data row43 col1" >0.344000</td>
+      <td id="T_a7af5_row43_col2" class="data row43 col2" >0.144000</td>
+      <td id="T_a7af5_row43_col3" class="data row43 col3" >0.160000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row46" class="row_heading level0 row46" >bbh_logical_deduction_three_objects.acc_norm</th>
+      <td id="T_a7af5_row46_col0" class="data row46 col0" >0.408000</td>
+      <td id="T_a7af5_row46_col1" class="data row46 col1" >0.692000</td>
+      <td id="T_a7af5_row46_col2" class="data row46 col2" >0.340000</td>
+      <td id="T_a7af5_row46_col3" class="data row46 col3" >0.484000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row49" class="row_heading level0 row49" >bbh_movie_recommendation.acc_norm</th>
+      <td id="T_a7af5_row49_col0" class="data row49 col0" >0.496000</td>
+      <td id="T_a7af5_row49_col1" class="data row49 col1" >0.584000</td>
+      <td id="T_a7af5_row49_col2" class="data row49 col2" >0.264000</td>
+      <td id="T_a7af5_row49_col3" class="data row49 col3" >0.296000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row52" class="row_heading level0 row52" >bbh_navigate.acc_norm</th>
+      <td id="T_a7af5_row52_col0" class="data row52 col0" >0.504000</td>
+      <td id="T_a7af5_row52_col1" class="data row52 col1" >0.680000</td>
+      <td id="T_a7af5_row52_col2" class="data row52 col2" >0.420000</td>
+      <td id="T_a7af5_row52_col3" class="data row52 col3" >0.484000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row55" class="row_heading level0 row55" >bbh_object_counting.acc_norm</th>
+      <td id="T_a7af5_row55_col0" class="data row55 col0" >0.336000</td>
+      <td id="T_a7af5_row55_col1" class="data row55 col1" >0.376000</td>
+      <td id="T_a7af5_row55_col2" class="data row55 col2" >0.356000</td>
+      <td id="T_a7af5_row55_col3" class="data row55 col3" >0.116000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row58" class="row_heading level0 row58" >bbh_penguins_in_a_table.acc_norm</th>
+      <td id="T_a7af5_row58_col0" class="data row58 col0" >0.253425</td>
+      <td id="T_a7af5_row58_col1" class="data row58 col1" >0.424658</td>
+      <td id="T_a7af5_row58_col2" class="data row58 col2" >0.212329</td>
+      <td id="T_a7af5_row58_col3" class="data row58 col3" >0.321918</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row61" class="row_heading level0 row61" >bbh_reasoning_about_colored_objects.acc_norm</th>
+      <td id="T_a7af5_row61_col0" class="data row61 col0" >0.272000</td>
+      <td id="T_a7af5_row61_col1" class="data row61 col1" >0.488000</td>
+      <td id="T_a7af5_row61_col2" class="data row61 col2" >0.192000</td>
+      <td id="T_a7af5_row61_col3" class="data row61 col3" >0.176000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row64" class="row_heading level0 row64" >bbh_ruin_names.acc_norm</th>
+      <td id="T_a7af5_row64_col0" class="data row64 col0" >0.216000</td>
+      <td id="T_a7af5_row64_col1" class="data row64 col1" >0.424000</td>
+      <td id="T_a7af5_row64_col2" class="data row64 col2" >0.232000</td>
+      <td id="T_a7af5_row64_col3" class="data row64 col3" >0.364000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row67" class="row_heading level0 row67" >bbh_salient_translation_error_detection.acc_norm</th>
+      <td id="T_a7af5_row67_col0" class="data row67 col0" >0.132000</td>
+      <td id="T_a7af5_row67_col1" class="data row67 col1" >0.264000</td>
+      <td id="T_a7af5_row67_col2" class="data row67 col2" >0.144000</td>
+      <td id="T_a7af5_row67_col3" class="data row67 col3" >0.220000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row70" class="row_heading level0 row70" >bbh_snarks.acc_norm</th>
+      <td id="T_a7af5_row70_col0" class="data row70 col0" >0.500000</td>
+      <td id="T_a7af5_row70_col1" class="data row70 col1" >0.516854</td>
+      <td id="T_a7af5_row70_col2" class="data row70 col2" >0.539326</td>
+      <td id="T_a7af5_row70_col3" class="data row70 col3" >0.477528</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row73" class="row_heading level0 row73" >bbh_sports_understanding.acc_norm</th>
+      <td id="T_a7af5_row73_col0" class="data row73 col0" >0.540000</td>
+      <td id="T_a7af5_row73_col1" class="data row73 col1" >0.564000</td>
+      <td id="T_a7af5_row73_col2" class="data row73 col2" >0.524000</td>
+      <td id="T_a7af5_row73_col3" class="data row73 col3" >0.480000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row76" class="row_heading level0 row76" >bbh_temporal_sequences.acc_norm</th>
+      <td id="T_a7af5_row76_col0" class="data row76 col0" >0.072000</td>
+      <td id="T_a7af5_row76_col1" class="data row76 col1" >0.132000</td>
+      <td id="T_a7af5_row76_col2" class="data row76 col2" >0.240000</td>
+      <td id="T_a7af5_row76_col3" class="data row76 col3" >0.244000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row79" class="row_heading level0 row79" >bbh_tracking_shuffled_objects_five_objects.acc_norm</th>
+      <td id="T_a7af5_row79_col0" class="data row79 col0" >0.212000</td>
+      <td id="T_a7af5_row79_col1" class="data row79 col1" >0.144000</td>
+      <td id="T_a7af5_row79_col2" class="data row79 col2" >0.224000</td>
+      <td id="T_a7af5_row79_col3" class="data row79 col3" >0.112000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row82" class="row_heading level0 row82" >bbh_tracking_shuffled_objects_seven_objects.acc_norm</th>
+      <td id="T_a7af5_row82_col0" class="data row82 col0" >0.168000</td>
+      <td id="T_a7af5_row82_col1" class="data row82 col1" >0.120000</td>
+      <td id="T_a7af5_row82_col2" class="data row82 col2" >0.152000</td>
+      <td id="T_a7af5_row82_col3" class="data row82 col3" >0.120000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row85" class="row_heading level0 row85" >bbh_tracking_shuffled_objects_three_objects.acc_norm</th>
+      <td id="T_a7af5_row85_col0" class="data row85 col0" >0.340000</td>
+      <td id="T_a7af5_row85_col1" class="data row85 col1" >0.320000</td>
+      <td id="T_a7af5_row85_col2" class="data row85 col2" >0.332000</td>
+      <td id="T_a7af5_row85_col3" class="data row85 col3" >0.304000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row88" class="row_heading level0 row88" >bbh_web_of_lies.acc_norm</th>
+      <td id="T_a7af5_row88_col0" class="data row88 col0" >0.488000</td>
+      <td id="T_a7af5_row88_col1" class="data row88 col1" >0.488000</td>
+      <td id="T_a7af5_row88_col2" class="data row88 col2" >0.488000</td>
+      <td id="T_a7af5_row88_col3" class="data row88 col3" >0.488000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row90" class="row_heading level0 row90" >gpqa.acc_norm</th>
+      <td id="T_a7af5_row90_col0" class="data row90 col0" >0.296980</td>
+      <td id="T_a7af5_row90_col1" class="data row90 col1" >0.337248</td>
+      <td id="T_a7af5_row90_col2" class="data row90 col2" >0.255872</td>
+      <td id="T_a7af5_row90_col3" class="data row90 col3" >0.279362</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row94" class="row_heading level0 row94" >gpqa_diamond.acc_norm</th>
+      <td id="T_a7af5_row94_col0" class="data row94 col0" >0.267677</td>
+      <td id="T_a7af5_row94_col1" class="data row94 col1" >0.318182</td>
+      <td id="T_a7af5_row94_col2" class="data row94 col2" >0.237374</td>
+      <td id="T_a7af5_row94_col3" class="data row94 col3" >0.232323</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row97" class="row_heading level0 row97" >gpqa_extended.acc_norm</th>
+      <td id="T_a7af5_row97_col0" class="data row97 col0" >0.313187</td>
+      <td id="T_a7af5_row97_col1" class="data row97 col1" >0.351648</td>
+      <td id="T_a7af5_row97_col2" class="data row97 col2" >0.239927</td>
+      <td id="T_a7af5_row97_col3" class="data row97 col3" >0.276557</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row100" class="row_heading level0 row100" >gpqa_main.acc_norm</th>
+      <td id="T_a7af5_row100_col0" class="data row100 col0" >0.290179</td>
+      <td id="T_a7af5_row100_col1" class="data row100 col1" >0.328125</td>
+      <td id="T_a7af5_row100_col2" class="data row100 col2" >0.283482</td>
+      <td id="T_a7af5_row100_col3" class="data row100 col3" >0.303571</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row103" class="row_heading level0 row103" >ifeval.prompt_level_strict_acc</th>
+      <td id="T_a7af5_row103_col0" class="data row103 col0" >0.188540</td>
+      <td id="T_a7af5_row103_col1" class="data row103 col1" >0.249538</td>
+      <td id="T_a7af5_row103_col2" class="data row103 col2" >0.275416</td>
+      <td id="T_a7af5_row103_col3" class="data row103 col3" >0.332717</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row105" class="row_heading level0 row105" >ifeval.inst_level_strict_acc</th>
+      <td id="T_a7af5_row105_col0" class="data row105 col0" >0.297362</td>
+      <td id="T_a7af5_row105_col1" class="data row105 col1" >0.381295</td>
+      <td id="T_a7af5_row105_col2" class="data row105 col2" >0.417266</td>
+      <td id="T_a7af5_row105_col3" class="data row105 col3" >0.474820</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row107" class="row_heading level0 row107" >ifeval.prompt_level_loose_acc</th>
+      <td id="T_a7af5_row107_col0" class="data row107 col0" >0.214418</td>
+      <td id="T_a7af5_row107_col1" class="data row107 col1" >0.314233</td>
+      <td id="T_a7af5_row107_col2" class="data row107 col2" >0.280961</td>
+      <td id="T_a7af5_row107_col3" class="data row107 col3" >0.340111</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row109" class="row_heading level0 row109" >ifeval.inst_level_loose_acc</th>
+      <td id="T_a7af5_row109_col0" class="data row109 col0" >0.323741</td>
+      <td id="T_a7af5_row109_col1" class="data row109 col1" >0.437650</td>
+      <td id="T_a7af5_row109_col2" class="data row109 col2" >0.423261</td>
+      <td id="T_a7af5_row109_col3" class="data row109 col3" >0.484412</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row111" class="row_heading level0 row111" >math_hard.exact_match</th>
+      <td id="T_a7af5_row111_col0" class="data row111 col0" >0.258308</td>
+      <td id="T_a7af5_row111_col1" class="data row111 col1" >0.388973</td>
+      <td id="T_a7af5_row111_col2" class="data row111 col2" >0.000000</td>
+      <td id="T_a7af5_row111_col3" class="data row111 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row115" class="row_heading level0 row115" >math_algebra_hard.exact_match</th>
+      <td id="T_a7af5_row115_col0" class="data row115 col0" >0.501629</td>
+      <td id="T_a7af5_row115_col1" class="data row115 col1" >0.618893</td>
+      <td id="T_a7af5_row115_col2" class="data row115 col2" >0.000000</td>
+      <td id="T_a7af5_row115_col3" class="data row115 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row118" class="row_heading level0 row118" >math_counting_and_prob_hard.exact_match</th>
+      <td id="T_a7af5_row118_col0" class="data row118 col0" >0.162602</td>
+      <td id="T_a7af5_row118_col1" class="data row118 col1" >0.349593</td>
+      <td id="T_a7af5_row118_col2" class="data row118 col2" >0.000000</td>
+      <td id="T_a7af5_row118_col3" class="data row118 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row121" class="row_heading level0 row121" >math_geometry_hard.exact_match</th>
+      <td id="T_a7af5_row121_col0" class="data row121 col0" >0.121212</td>
+      <td id="T_a7af5_row121_col1" class="data row121 col1" >0.250000</td>
+      <td id="T_a7af5_row121_col2" class="data row121 col2" >0.000000</td>
+      <td id="T_a7af5_row121_col3" class="data row121 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row124" class="row_heading level0 row124" >math_intermediate_algebra_hard.exact_match</th>
+      <td id="T_a7af5_row124_col0" class="data row124 col0" >0.064286</td>
+      <td id="T_a7af5_row124_col1" class="data row124 col1" >0.153571</td>
+      <td id="T_a7af5_row124_col2" class="data row124 col2" >0.000000</td>
+      <td id="T_a7af5_row124_col3" class="data row124 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row127" class="row_heading level0 row127" >math_num_theory_hard.exact_match</th>
+      <td id="T_a7af5_row127_col0" class="data row127 col0" >0.266234</td>
+      <td id="T_a7af5_row127_col1" class="data row127 col1" >0.415584</td>
+      <td id="T_a7af5_row127_col2" class="data row127 col2" >0.000000</td>
+      <td id="T_a7af5_row127_col3" class="data row127 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row130" class="row_heading level0 row130" >math_prealgebra_hard.exact_match</th>
+      <td id="T_a7af5_row130_col0" class="data row130 col0" >0.430052</td>
+      <td id="T_a7af5_row130_col1" class="data row130 col1" >0.647668</td>
+      <td id="T_a7af5_row130_col2" class="data row130 col2" >0.000000</td>
+      <td id="T_a7af5_row130_col3" class="data row130 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row133" class="row_heading level0 row133" >math_precalculus_hard.exact_match</th>
+      <td id="T_a7af5_row133_col0" class="data row133 col0" >0.074074</td>
+      <td id="T_a7af5_row133_col1" class="data row133 col1" >0.125926</td>
+      <td id="T_a7af5_row133_col2" class="data row133 col2" >0.000000</td>
+      <td id="T_a7af5_row133_col3" class="data row133 col3" >0.000000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row136" class="row_heading level0 row136" >mmlu_pro.acc</th>
+      <td id="T_a7af5_row136_col0" class="data row136 col0" >0.192487</td>
+      <td id="T_a7af5_row136_col1" class="data row136 col1" >0.297041</td>
+      <td id="T_a7af5_row136_col2" class="data row136 col2" >0.118684</td>
+      <td id="T_a7af5_row136_col3" class="data row136 col3" >0.232131</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row138" class="row_heading level0 row138" >musr.acc_norm</th>
+      <td id="T_a7af5_row138_col0" class="data row138 col0" >0.334656</td>
+      <td id="T_a7af5_row138_col1" class="data row138 col1" >0.390212</td>
+      <td id="T_a7af5_row138_col2" class="data row138 col2" >0.362434</td>
+      <td id="T_a7af5_row138_col3" class="data row138 col3" >0.365079</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row142" class="row_heading level0 row142" >musr_murder_mysteries.acc_norm</th>
+      <td id="T_a7af5_row142_col0" class="data row142 col0" >0.504000</td>
+      <td id="T_a7af5_row142_col1" class="data row142 col1" >0.520000</td>
+      <td id="T_a7af5_row142_col2" class="data row142 col2" >0.492000</td>
+      <td id="T_a7af5_row142_col3" class="data row142 col3" >0.492000</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row145" class="row_heading level0 row145" >musr_object_placements.acc_norm</th>
+      <td id="T_a7af5_row145_col0" class="data row145 col0" >0.238281</td>
+      <td id="T_a7af5_row145_col1" class="data row145 col1" >0.281250</td>
+      <td id="T_a7af5_row145_col2" class="data row145 col2" >0.234375</td>
+      <td id="T_a7af5_row145_col3" class="data row145 col3" >0.214844</td>
+    </tr>
+    <tr>
+      <th id="T_a7af5_level0_row148" class="row_heading level0 row148" >musr_team_allocation.acc_norm</th>
+      <td id="T_a7af5_row148_col0" class="data row148 col0" >0.264000</td>
+      <td id="T_a7af5_row148_col1" class="data row148 col1" >0.372000</td>
+      <td id="T_a7af5_row148_col2" class="data row148 col2" >0.364000</td>
+      <td id="T_a7af5_row148_col3" class="data row148 col3" >0.392000</td>
+    </tr>
+  </tbody>
+</table>