| queries_arc_challenge_bin_scores_correct.csv | 58.3 kB | | 76ceb747 |
| queries_arc_challenge_bin_scores_incorrect.csv | 58.4 kB | | 9de1e78e |
| queries_arc_combined_bin_scores_correct.csv | 58.3 kB | | bb26eac6 |
| queries_arc_combined_bin_scores_incorrect.csv | 58.4 kB | | 0f91a629 |
| queries_arc_easy_bin_scores_correct.csv | 58.3 kB | | 1664eaae |
| queries_arc_easy_bin_scores_incorrect.csv | 58.4 kB | | fee9d019 |
| queries_gsm8k_bin_scores_correct.csv | 58.5 kB | | bbe8fb4b |
| queries_gsm8k_bin_scores_incorrect.csv | 58.4 kB | | f11002d9 |
| queries_mmlu_social_science_bin_scores_correct.csv | 58.8 kB | | 4062da21 |
| queries_mmlu_social_science_bin_scores_incorrect.csv | 58.9 kB | | 8180b4a8 |
| queries_mmlu_stem_bin_scores_correct.csv | 58.9 kB | | 64327e40 |
| queries_mmlu_stem_bin_scores_incorrect.csv | 58.8 kB | | a0345b36 |
| queries_socialiqa_bin_scores_correct.csv | 58.7 kB | | 218c5a3e |
| queries_socialiqa_bin_scores_incorrect.csv | 59 kB | | 6d832303 |