Update README.md
Browse files
README.md
CHANGED
|
@@ -77,3 +77,54 @@ print(outputs[0]["generated_text"])
|
|
| 77 |
</div>
|
| 78 |
</div>
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
</div>
|
| 78 |
</div>
|
| 79 |
|
| 80 |
+
## OpenLLM Leaderboard Metrics (WIP)
|
| 81 |
+
|
| 82 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 83 |
+
|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------|
|
| 84 |
+
|leaderboard | N/A| | | | | | | |
|
| 85 |
+
| - leaderboard_bbh | N/A| | | | | | | |
|
| 86 |
+
| - leaderboard_bbh_boolean_expressions | 1|none | 3|acc_norm |↑ |0.6840|± |0.0295|
|
| 87 |
+
| - leaderboard_bbh_causal_judgement | 1|none | 3|acc_norm |↑ |0.5134|± |0.0366|
|
| 88 |
+
| - leaderboard_bbh_date_understanding | 1|none | 3|acc_norm |↑ |0.1920|± |0.0250|
|
| 89 |
+
| - leaderboard_bbh_disambiguation_qa | 1|none | 3|acc_norm |↑ |0.3880|± |0.0309|
|
| 90 |
+
| - leaderboard_bbh_formal_fallacies | 1|none | 3|acc_norm |↑ |0.4680|± |0.0316|
|
| 91 |
+
| - leaderboard_bbh_geometric_shapes | 1|none | 3|acc_norm |↑ |0.0000|± | 0|
|
| 92 |
+
| - leaderboard_bbh_hyperbaton | 1|none | 3|acc_norm |↑ |0.4840|± |0.0317|
|
| 93 |
+
| - leaderboard_bbh_logical_deduction_five_objects | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
| 94 |
+
| - leaderboard_bbh_logical_deduction_seven_objects | 1|none | 3|acc_norm |↑ |0.1360|± |0.0217|
|
| 95 |
+
| - leaderboard_bbh_logical_deduction_three_objects | 1|none | 3|acc_norm |↑ |0.3440|± |0.0301|
|
| 96 |
+
| - leaderboard_bbh_movie_recommendation | 1|none | 3|acc_norm |↑ |0.2280|± |0.0266|
|
| 97 |
+
| - leaderboard_bbh_navigate | 1|none | 3|acc_norm |↑ |0.4200|± |0.0313|
|
| 98 |
+
| - leaderboard_bbh_object_counting | 1|none | 3|acc_norm |↑ |0.3880|± |0.0309|
|
| 99 |
+
| - leaderboard_bbh_penguins_in_a_table | 1|none | 3|acc_norm |↑ |0.1575|± |0.0303|
|
| 100 |
+
| - leaderboard_bbh_reasoning_about_colored_objects | 1|none | 3|acc_norm |↑ |0.1280|± |0.0212|
|
| 101 |
+
| - leaderboard_bbh_ruin_names | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
| 102 |
+
| - leaderboard_bbh_salient_translation_error_detection | 1|none | 3|acc_norm |↑ |0.2280|± |0.0266|
|
| 103 |
+
| - leaderboard_bbh_snarks | 1|none | 3|acc_norm |↑ |0.5393|± |0.0375|
|
| 104 |
+
| - leaderboard_bbh_sports_understanding | 1|none | 3|acc_norm |↑ |0.5240|± |0.0316|
|
| 105 |
+
| - leaderboard_bbh_temporal_sequences | 1|none | 3|acc_norm |↑ |0.2000|± |0.0253|
|
| 106 |
+
| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 1|none | 3|acc_norm |↑ |0.1640|± |0.0235|
|
| 107 |
+
| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 1|none | 3|acc_norm |↑ |0.1400|± |0.0220|
|
| 108 |
+
| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 1|none | 3|acc_norm |↑ |0.3520|± |0.0303|
|
| 109 |
+
| - leaderboard_bbh_web_of_lies | 1|none | 3|acc_norm |↑ |0.4880|± |0.0317|
|
| 110 |
+
| - leaderboard_gpqa | N/A| | | | | | | |
|
| 111 |
+
| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2576|± |0.0312|
|
| 112 |
+
| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2436|± |0.0184|
|
| 113 |
+
| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2433|± |0.0203|
|
| 114 |
+
| - leaderboard_ifeval | 3|none | 0|inst_level_loose_acc |↑ |0.2962|± | N/A|
|
| 115 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.2842|± | N/A|
|
| 116 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.1516|± |0.0154|
|
| 117 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.1386|± |0.0149|
|
| 118 |
+
| - leaderboard_math_hard | N/A| | | | | | | |
|
| 119 |
+
| - leaderboard_math_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 120 |
+
| - leaderboard_math_counting_and_prob_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 121 |
+
| - leaderboard_math_geometry_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 122 |
+
| - leaderboard_math_intermediate_algebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 123 |
+
| - leaderboard_math_num_theory_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 124 |
+
| - leaderboard_math_prealgebra_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 125 |
+
| - leaderboard_math_precalculus_hard | 2|none | 4|exact_match |↑ |0.0000|± | 0|
|
| 126 |
+
| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.1222|± |0.0030|
|
| 127 |
+
| - leaderboard_musr | N/A| | | | | | | |
|
| 128 |
+
| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5120|± |0.0317|
|
| 129 |
+
| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.2500|± |0.0271|
|
| 130 |
+
| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.2680|± |0.0281|
|