Update README.md
Browse files
README.md
CHANGED
|
@@ -207,4 +207,108 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 207 |
|MATH Lvl 5 (4-Shot)| 6.04|
|
| 208 |
|GPQA (0-shot) |15.21|
|
| 209 |
|MuSR (0-shot) |13.61|
|
| 210 |
-
|MMLU-PRO (5-shot) |46.85|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
|MATH Lvl 5 (4-Shot)| 6.04|
|
| 208 |
|GPQA (0-shot) |15.21|
|
| 209 |
|MuSR (0-shot) |13.61|
|
| 210 |
+
|MMLU-PRO (5-shot) |46.85|
|
| 211 |
+
|
| 212 |
+
|
| 213 |
+
| Key | 72b Result | 95b Result | Difference | Which is Higher | Multiplier |
|
| 214 |
+
|:--------------------------------------------------------------------------|-------------:|-------------:|-------------:|:------------------|:-------------|
|
| 215 |
+
| leaderboard_musr.acc_norm,none | 0.419 | 0.427 | 0.008 | 95b | 1.02x |
|
| 216 |
+
| leaderboard_bbh_sports_understanding.acc_norm,none | 0.892 | 0.876 | 0.016 | 72b | 0.98x |
|
| 217 |
+
| leaderboard_bbh_logical_deduction_three_objects.acc_norm,none | 0.94 | 0.928 | 0.012 | 72b | 0.99x |
|
| 218 |
+
| leaderboard_math_geometry_hard.exact_match,none | 0 | 0.008 | 0.008 | 95b | 0.00x |
|
| 219 |
+
| leaderboard_gpqa.acc_norm,none | 0.375 | 0.364 | 0.011 | 72b | 0.97x |
|
| 220 |
+
| leaderboard_math_hard.exact_match,none | 0.012 | 0.06 | 0.048 | 95b | 5.00x |
|
| 221 |
+
| leaderboard.exact_match,none | 0.012 | 0.06 | 0.048 | 95b | 5.00x |
|
| 222 |
+
| leaderboard.prompt_level_loose_acc,none | 0.861 | 0.839 | 0.022 | 72b | 0.97x |
|
| 223 |
+
| leaderboard.prompt_level_strict_acc,none | 0.839 | 0.813 | 0.026 | 72b | 0.97x |
|
| 224 |
+
| leaderboard.inst_level_loose_acc,none | 0.904 | 0.891 | 0.013 | 72b | 0.99x |
|
| 225 |
+
| leaderboard.acc_norm,none | 0.641 | 0.622 | 0.02 | 72b | 0.97x |
|
| 226 |
+
| leaderboard.inst_level_strict_acc,none | 0.888 | 0.873 | 0.016 | 72b | 0.98x |
|
| 227 |
+
| leaderboard.acc,none | 0.563 | 0.522 | 0.041 | 72b | 0.93x |
|
| 228 |
+
| leaderboard_bbh_causal_judgement.acc_norm,none | 0.668 | 0.663 | 0.005 | 72b | 0.99x |
|
| 229 |
+
| leaderboard_bbh_salient_translation_error_detection.acc_norm,none | 0.668 | 0.588 | 0.08 | 72b | 0.88x |
|
| 230 |
+
| leaderboard_gpqa_extended.acc_norm,none | 0.372 | 0.364 | 0.007 | 72b | 0.98x |
|
| 231 |
+
| leaderboard_math_prealgebra_hard.exact_match,none | 0.047 | 0.155 | 0.109 | 95b | 3.33x |
|
| 232 |
+
| leaderboard_math_algebra_hard.exact_match,none | 0.02 | 0.114 | 0.094 | 95b | 5.83x |
|
| 233 |
+
| leaderboard_bbh_boolean_expressions.acc_norm,none | 0.936 | 0.92 | 0.016 | 72b | 0.98x |
|
| 234 |
+
| leaderboard_math_num_theory_hard.exact_match,none | 0 | 0.058 | 0.058 | 95b | 0.00x |
|
| 235 |
+
| leaderboard_bbh_movie_recommendation.acc_norm,none | 0.768 | 0.78 | 0.012 | 95b | 1.02x |
|
| 236 |
+
| leaderboard_math_counting_and_prob_hard.exact_match,none | 0 | 0.024 | 0.024 | 95b | 0.00x |
|
| 237 |
+
| leaderboard_math_intermediate_algebra_hard.exact_match,none | 0 | 0.004 | 0.004 | 95b | 0.00x |
|
| 238 |
+
| leaderboard_ifeval.prompt_level_strict_acc,none | 0.839 | 0.813 | 0.026 | 72b | 0.97x |
|
| 239 |
+
| leaderboard_ifeval.inst_level_strict_acc,none | 0.888 | 0.873 | 0.016 | 72b | 0.98x |
|
| 240 |
+
| leaderboard_ifeval.inst_level_loose_acc,none | 0.904 | 0.891 | 0.013 | 72b | 0.99x |
|
| 241 |
+
| leaderboard_ifeval.prompt_level_loose_acc,none | 0.861 | 0.839 | 0.022 | 72b | 0.97x |
|
| 242 |
+
| leaderboard_bbh_snarks.acc_norm,none | 0.927 | 0.904 | 0.022 | 72b | 0.98x |
|
| 243 |
+
| leaderboard_bbh_web_of_lies.acc_norm,none | 0.676 | 0.616 | 0.06 | 72b | 0.91x |
|
| 244 |
+
| leaderboard_bbh_penguins_in_a_table.acc_norm,none | 0.719 | 0.767 | 0.048 | 95b | 1.07x |
|
| 245 |
+
| leaderboard_bbh_hyperbaton.acc_norm,none | 0.892 | 0.9 | 0.008 | 95b | 1.01x |
|
| 246 |
+
| leaderboard_bbh_object_counting.acc_norm,none | 0.612 | 0.544 | 0.068 | 72b | 0.89x |
|
| 247 |
+
| leaderboard_musr_object_placements.acc_norm,none | 0.258 | 0.285 | 0.027 | 95b | 1.11x |
|
| 248 |
+
| leaderboard_bbh_logical_deduction_five_objects.acc_norm,none | 0.704 | 0.592 | 0.112 | 72b | 0.84x |
|
| 249 |
+
| leaderboard_musr_team_allocation.acc_norm,none | 0.456 | 0.396 | 0.06 | 72b | 0.87x |
|
| 250 |
+
| leaderboard_bbh_navigate.acc_norm,none | 0.832 | 0.788 | 0.044 | 72b | 0.95x |
|
| 251 |
+
| leaderboard_bbh_tracking_shuffled_objects_seven_objects.acc_norm,none | 0.34 | 0.304 | 0.036 | 72b | 0.89x |
|
| 252 |
+
| leaderboard_bbh_formal_fallacies.acc_norm,none | 0.776 | 0.756 | 0.02 | 72b | 0.97x |
|
| 253 |
+
| all.leaderboard_musr.acc_norm,none | 0.419 | 0.427 | 0.008 | 95b | 1.02x |
|
| 254 |
+
| all.leaderboard_bbh_sports_understanding.acc_norm,none | 0.892 | 0.876 | 0.016 | 72b | 0.98x |
|
| 255 |
+
| all.leaderboard_bbh_logical_deduction_three_objects.acc_norm,none | 0.94 | 0.928 | 0.012 | 72b | 0.99x |
|
| 256 |
+
| all.leaderboard_math_geometry_hard.exact_match,none | 0 | 0.008 | 0.008 | 95b | 0.00x |
|
| 257 |
+
| all.leaderboard_gpqa.acc_norm,none | 0.375 | 0.364 | 0.011 | 72b | 0.97x |
|
| 258 |
+
| all.leaderboard_math_hard.exact_match,none | 0.012 | 0.06 | 0.048 | 95b | 5.00x |
|
| 259 |
+
| all.leaderboard.exact_match,none | 0.012 | 0.06 | 0.048 | 95b | 5.00x |
|
| 260 |
+
| all.leaderboard.prompt_level_loose_acc,none | 0.861 | 0.839 | 0.022 | 72b | 0.97x |
|
| 261 |
+
| all.leaderboard.prompt_level_strict_acc,none | 0.839 | 0.813 | 0.026 | 72b | 0.97x |
|
| 262 |
+
| all.leaderboard.inst_level_loose_acc,none | 0.904 | 0.891 | 0.013 | 72b | 0.99x |
|
| 263 |
+
| all.leaderboard.acc_norm,none | 0.641 | 0.622 | 0.02 | 72b | 0.97x |
|
| 264 |
+
| all.leaderboard.inst_level_strict_acc,none | 0.888 | 0.873 | 0.016 | 72b | 0.98x |
|
| 265 |
+
| all.leaderboard.acc,none | 0.563 | 0.522 | 0.041 | 72b | 0.93x |
|
| 266 |
+
| all.leaderboard_bbh_causal_judgement.acc_norm,none | 0.668 | 0.663 | 0.005 | 72b | 0.99x |
|
| 267 |
+
| all.leaderboard_bbh_salient_translation_error_detection.acc_norm,none | 0.668 | 0.588 | 0.08 | 72b | 0.88x |
|
| 268 |
+
| all.leaderboard_gpqa_extended.acc_norm,none | 0.372 | 0.364 | 0.007 | 72b | 0.98x |
|
| 269 |
+
| all.leaderboard_math_prealgebra_hard.exact_match,none | 0.047 | 0.155 | 0.109 | 95b | 3.33x |
|
| 270 |
+
| all.leaderboard_math_algebra_hard.exact_match,none | 0.02 | 0.114 | 0.094 | 95b | 5.83x |
|
| 271 |
+
| all.leaderboard_bbh_boolean_expressions.acc_norm,none | 0.936 | 0.92 | 0.016 | 72b | 0.98x |
|
| 272 |
+
| all.leaderboard_math_num_theory_hard.exact_match,none | 0 | 0.058 | 0.058 | 95b | 0.00x |
|
| 273 |
+
| all.leaderboard_bbh_movie_recommendation.acc_norm,none | 0.768 | 0.78 | 0.012 | 95b | 1.02x |
|
| 274 |
+
| all.leaderboard_math_counting_and_prob_hard.exact_match,none | 0 | 0.024 | 0.024 | 95b | 0.00x |
|
| 275 |
+
| all.leaderboard_math_intermediate_algebra_hard.exact_match,none | 0 | 0.004 | 0.004 | 95b | 0.00x |
|
| 276 |
+
| all.leaderboard_ifeval.prompt_level_strict_acc,none | 0.839 | 0.813 | 0.026 | 72b | 0.97x |
|
| 277 |
+
| all.leaderboard_ifeval.inst_level_strict_acc,none | 0.888 | 0.873 | 0.016 | 72b | 0.98x |
|
| 278 |
+
| all.leaderboard_ifeval.inst_level_loose_acc,none | 0.904 | 0.891 | 0.013 | 72b | 0.99x |
|
| 279 |
+
| all.leaderboard_ifeval.prompt_level_loose_acc,none | 0.861 | 0.839 | 0.022 | 72b | 0.97x |
|
| 280 |
+
| all.leaderboard_bbh_snarks.acc_norm,none | 0.927 | 0.904 | 0.022 | 72b | 0.98x |
|
| 281 |
+
| all.leaderboard_bbh_web_of_lies.acc_norm,none | 0.676 | 0.616 | 0.06 | 72b | 0.91x |
|
| 282 |
+
| all.leaderboard_bbh_penguins_in_a_table.acc_norm,none | 0.719 | 0.767 | 0.048 | 95b | 1.07x |
|
| 283 |
+
| all.leaderboard_bbh_hyperbaton.acc_norm,none | 0.892 | 0.9 | 0.008 | 95b | 1.01x |
|
| 284 |
+
| all.leaderboard_bbh_object_counting.acc_norm,none | 0.612 | 0.544 | 0.068 | 72b | 0.89x |
|
| 285 |
+
| all.leaderboard_musr_object_placements.acc_norm,none | 0.258 | 0.285 | 0.027 | 95b | 1.11x |
|
| 286 |
+
| all.leaderboard_bbh_logical_deduction_five_objects.acc_norm,none | 0.704 | 0.592 | 0.112 | 72b | 0.84x |
|
| 287 |
+
| all.leaderboard_musr_team_allocation.acc_norm,none | 0.456 | 0.396 | 0.06 | 72b | 0.87x |
|
| 288 |
+
| all.leaderboard_bbh_navigate.acc_norm,none | 0.832 | 0.788 | 0.044 | 72b | 0.95x |
|
| 289 |
+
| all.leaderboard_bbh_tracking_shuffled_objects_seven_objects.acc_norm,none | 0.34 | 0.304 | 0.036 | 72b | 0.89x |
|
| 290 |
+
| all.leaderboard_bbh_formal_fallacies.acc_norm,none | 0.776 | 0.756 | 0.02 | 72b | 0.97x |
|
| 291 |
+
| all.leaderboard_gpqa_main.acc_norm,none | 0.375 | 0.355 | 0.02 | 72b | 0.95x |
|
| 292 |
+
| all.leaderboard_bbh_disambiguation_qa.acc_norm,none | 0.744 | 0.772 | 0.028 | 95b | 1.04x |
|
| 293 |
+
| all.leaderboard_bbh_tracking_shuffled_objects_five_objects.acc_norm,none | 0.32 | 0.284 | 0.036 | 72b | 0.89x |
|
| 294 |
+
| all.leaderboard_bbh_date_understanding.acc_norm,none | 0.784 | 0.764 | 0.02 | 72b | 0.97x |
|
| 295 |
+
| all.leaderboard_bbh_geometric_shapes.acc_norm,none | 0.464 | 0.412 | 0.052 | 72b | 0.89x |
|
| 296 |
+
| all.leaderboard_bbh_reasoning_about_colored_objects.acc_norm,none | 0.864 | 0.84 | 0.024 | 72b | 0.97x |
|
| 297 |
+
| all.leaderboard_musr_murder_mysteries.acc_norm,none | 0.548 | 0.604 | 0.056 | 95b | 1.10x |
|
| 298 |
+
| all.leaderboard_bbh_ruin_names.acc_norm,none | 0.888 | 0.86 | 0.028 | 72b | 0.97x |
|
| 299 |
+
| all.leaderboard_bbh_logical_deduction_seven_objects.acc_norm,none | 0.644 | 0.664 | 0.02 | 95b | 1.03x |
|
| 300 |
+
| all.leaderboard_bbh.acc_norm,none | 0.726 | 0.701 | 0.025 | 72b | 0.97x |
|
| 301 |
+
| all.leaderboard_bbh_temporal_sequences.acc_norm,none | 0.996 | 0.968 | 0.028 | 72b | 0.97x |
|
| 302 |
+
| all.leaderboard_mmlu_pro.acc,none | 0.563 | 0.522 | 0.041 | 72b | 0.93x |
|
| 303 |
+
| leaderboard_gpqa_main.acc_norm,none | 0.375 | 0.355 | 0.02 | 72b | 0.95x |
|
| 304 |
+
| leaderboard_bbh_disambiguation_qa.acc_norm,none | 0.744 | 0.772 | 0.028 | 95b | 1.04x |
|
| 305 |
+
| leaderboard_bbh_tracking_shuffled_objects_five_objects.acc_norm,none | 0.32 | 0.284 | 0.036 | 72b | 0.89x |
|
| 306 |
+
| leaderboard_bbh_date_understanding.acc_norm,none | 0.784 | 0.764 | 0.02 | 72b | 0.97x |
|
| 307 |
+
| leaderboard_bbh_geometric_shapes.acc_norm,none | 0.464 | 0.412 | 0.052 | 72b | 0.89x |
|
| 308 |
+
| leaderboard_bbh_reasoning_about_colored_objects.acc_norm,none | 0.864 | 0.84 | 0.024 | 72b | 0.97x |
|
| 309 |
+
| leaderboard_musr_murder_mysteries.acc_norm,none | 0.548 | 0.604 | 0.056 | 95b | 1.10x |
|
| 310 |
+
| leaderboard_bbh_ruin_names.acc_norm,none | 0.888 | 0.86 | 0.028 | 72b | 0.97x |
|
| 311 |
+
| leaderboard_bbh_logical_deduction_seven_objects.acc_norm,none | 0.644 | 0.664 | 0.02 | 95b | 1.03x |
|
| 312 |
+
| leaderboard_bbh.acc_norm,none | 0.726 | 0.701 | 0.025 | 72b | 0.97x |
|
| 313 |
+
| leaderboard_bbh_temporal_sequences.acc_norm,none | 0.996 | 0.968 | 0.028 | 72b | 0.97x |
|
| 314 |
+
| leaderboard_mmlu_pro.acc,none | 0.563 | 0.522 | 0.041 | 72b | 0.93x |
|