| metrics-all.jsonl | 117 kB | | 94b0e398 |
| metrics.json | 55.9 kB | | f4ad1a49 |
| task-000-mmlu_moral_scenarios:mc-metrics.json | 2.08 kB | | ba5d0691 |
| task-000-mmlu_moral_scenarios:mc-predictions.jsonl | 1.39 MB | | 8ae04c1c |
| task-000-mmlu_moral_scenarios:mc-recorded-inputs.jsonl | 35.6 kB | | 3a08baa9 |
| task-001-mmlu_moral_disputes:mc-metrics.json | 2.07 kB | | 2cc47fd7 |
| task-001-mmlu_moral_disputes:mc-predictions.jsonl | 537 kB | | fa711e16 |
| task-001-mmlu_moral_disputes:mc-recorded-inputs.jsonl | 29.3 kB | | bd5bab8f |
| task-002-mmlu_philosophy:mc-metrics.json | 2.05 kB | | dc86539a |
| task-002-mmlu_philosophy:mc-predictions.jsonl | 483 kB | | de551e07 |
| task-002-mmlu_philosophy:mc-recorded-inputs.jsonl | 18.6 kB | | 1e433f33 |
| task-003-mmlu_business_ethics:mc-metrics.json | 2.01 kB | | ba8577bd |
| task-003-mmlu_business_ethics:mc-predictions.jsonl | 155 kB | | 242a2ced |
| task-003-mmlu_business_ethics:mc-recorded-inputs.jsonl | 35.9 kB | | 3abb1208 |
| task-004-ethics_commonsense:mc-metrics.json | 2.11 kB | | b21cd0e2 |
| task-004-ethics_commonsense:mc-predictions.jsonl | 4.24 MB | | 5395adb0 |
| task-004-ethics_commonsense:mc-recorded-inputs.jsonl | 2.27 kB | | 745cf2a0 |
| task-005-ethics_deontology:mc-metrics.json | 2.1 kB | | 4f14bc6c |
| task-005-ethics_deontology:mc-predictions.jsonl | 3.92 MB | | 0f8f6907 |
| task-005-ethics_deontology:mc-recorded-inputs.jsonl | 2.82 kB | | 7494bde9 |
| task-006-ethics_justice:mc-metrics.json | 2.1 kB | | b10d2142 |
| task-006-ethics_justice:mc-predictions.jsonl | 2.95 MB | | cdd7be7d |
| task-006-ethics_justice:mc-recorded-inputs.jsonl | 2.97 kB | | fc0ffb22 |
| task-007-ethics_utilitarianism:mc-metrics.json | 2.12 kB | | a106f5fe |
| task-007-ethics_utilitarianism:mc-predictions.jsonl | 5.24 MB | | 5cd74133 |
| task-007-ethics_utilitarianism:mc-recorded-inputs.jsonl | 3.49 kB | | 674da13e |
| task-008-ethics_virtue:mc-metrics.json | 2.09 kB | | 256a89dd |
| task-008-ethics_virtue:mc-predictions.jsonl | 5.43 MB | | db19fc82 |
| task-008-ethics_virtue:mc-recorded-inputs.jsonl | 2.87 kB | | b39bfe5a |
| task-009-bbq:mc-metrics.json | 2.02 kB | | 74a057e1 |
| task-009-bbq:mc-predictions.jsonl | 78.1 MB | | 722e0378 |
| task-009-bbq:mc-recorded-inputs.jsonl | 6.14 kB | | 38141c5b |
| task-010-tombench:mc-metrics.json | 2.05 kB | | 84b74a95 |
| task-010-tombench:mc-predictions.jsonl | 4.01 MB | | 0d87ebc8 |
| task-010-tombench:mc-recorded-inputs.jsonl | 7.31 kB | | b47e2e05 |
| task-011-morables:mc-metrics.json | 2.04 kB | | e7e659b0 |
| task-011-morables:mc-predictions.jsonl | 1.27 MB | | 3d8b8c85 |
| task-011-morables:mc-recorded-inputs.jsonl | 28.1 kB | | c5b570c7 |
| task-012-negotiationtom_desire:mc-metrics.json | 2.1 kB | | 8409b89d |
| task-012-negotiationtom_desire:mc-predictions.jsonl | 26.1 MB | | dd2ed808 |
| task-012-negotiationtom_desire:mc-recorded-inputs.jsonl | 10.3 kB | | ff925e4b |
| task-013-negotiationtom_belief:mc-metrics.json | 2.09 kB | | ab3d1bc4 |
| task-013-negotiationtom_belief:mc-predictions.jsonl | 26.1 MB | | f43be2e5 |
| task-013-negotiationtom_belief:mc-recorded-inputs.jsonl | 10.9 kB | | 2509a241 |
| task-014-pub_1:mc-metrics.json | 1.97 kB | | e8e10116 |
| task-014-pub_1:mc-predictions.jsonl | 2.73 MB | | 10a7bf06 |
| task-014-pub_1:mc-recorded-inputs.jsonl | 3.29 kB | | c8b791ac |
| task-015-pub_2:mc-metrics.json | 2.03 kB | | c741236b |
| task-015-pub_2:mc-predictions.jsonl | 4.45 MB | | 8b8071ee |
| task-015-pub_2:mc-recorded-inputs.jsonl | 7.26 kB | | e65ae27b |
| task-016-pub_3:mc-metrics.json | 2.03 kB | | aba995ef |
| task-016-pub_3:mc-predictions.jsonl | 4.45 MB | | 1bf86df5 |
| task-016-pub_3:mc-recorded-inputs.jsonl | 8.64 kB | | f300bfb4 |
| task-017-pub_4:mc-metrics.json | 1.97 kB | | af814bbf |
| task-017-pub_4:mc-predictions.jsonl | 3.11 MB | | 52bd611d |
| task-017-pub_4:mc-recorded-inputs.jsonl | 14.8 kB | | 87c0c712 |
| task-018-pub_5:mc-metrics.json | 1.96 kB | | 2ad2453a |
| task-018-pub_5:mc-predictions.jsonl | 2.19 MB | | f9934e42 |
| task-018-pub_5:mc-recorded-inputs.jsonl | 2.48 kB | | 0afc8e86 |
| task-019-pub_6:mc-metrics.json | 1.96 kB | | b23f960b |
| task-019-pub_6:mc-predictions.jsonl | 2.19 MB | | caaf06c7 |
| task-019-pub_6:mc-recorded-inputs.jsonl | 2.54 kB | | aec9a298 |
| task-020-pub_7:mc-metrics.json | 2.03 kB | | e3e22a9a |
| task-020-pub_7:mc-predictions.jsonl | 1.94 MB | | c6f95e8c |
| task-020-pub_7:mc-recorded-inputs.jsonl | 4.82 kB | | 2bae9702 |
| task-021-pub_8:mc-metrics.json | 2.03 kB | | 02b810d8 |
| task-021-pub_8:mc-predictions.jsonl | 1.94 MB | | 48013c9d |
| task-021-pub_8:mc-recorded-inputs.jsonl | 6.13 kB | | c37887de |
| task-022-pub_9:mc-metrics.json | 2.03 kB | | a205fb6f |
| task-022-pub_9:mc-predictions.jsonl | 1.94 MB | | e6b5ce05 |
| task-022-pub_9:mc-recorded-inputs.jsonl | 6.21 kB | | a88cf01d |
| task-023-pub_10:mc-metrics.json | 2.04 kB | | 76c23d56 |
| task-023-pub_10:mc-predictions.jsonl | 2.78 MB | | 2182f9b8 |
| task-023-pub_10:mc-recorded-inputs.jsonl | 4.48 kB | | c06522b2 |
| task-024-pub_11:mc-metrics.json | 2.03 kB | | 600ccbc6 |
| task-024-pub_11:mc-predictions.jsonl | 2.38 MB | | 4766a3ae |
| task-024-pub_11:mc-recorded-inputs.jsonl | 4.79 kB | | eebe8e27 |
| task-025-pub_12:mc-metrics.json | 2.03 kB | | 414c977c |
| task-025-pub_12:mc-predictions.jsonl | 2.81 MB | | 8cfa2f5f |
| task-025-pub_12:mc-recorded-inputs.jsonl | 4.49 kB | | a581ea5c |
| task-026-pub_13:mc-metrics.json | 1.97 kB | | 8f744212 |
| task-026-pub_13:mc-predictions.jsonl | 1.1 MB | | 584783b0 |
| task-026-pub_13:mc-recorded-inputs.jsonl | 9.25 kB | | 9a7ab8b5 |
| task-027-pub_14:mc-metrics.json | 2.03 kB | | 9601efb8 |
| task-027-pub_14:mc-predictions.jsonl | 707 kB | | bdd84f4a |
| task-027-pub_14:mc-recorded-inputs.jsonl | 4.76 kB | | 4237b685 |
| task-028-socialiqa:mc-metrics.json | 1.93 kB | | 333c8178 |
| task-028-socialiqa:mc-predictions.jsonl | 13.3 MB | | a04b3f28 |
| task-028-socialiqa:mc-recorded-inputs.jsonl | 14.3 kB | | a3682757 |
| task-029-mmlu_abstract_algebra:mc-metrics.json | 2.01 kB | | 08230d52 |
| task-029-mmlu_abstract_algebra:mc-predictions.jsonl | 155 kB | | a10bd9c9 |
| task-029-mmlu_abstract_algebra:mc-recorded-inputs.jsonl | 16.1 kB | | 54119acf |
| task-030-mmlu_astronomy:mc-metrics.json | 2.04 kB | | 8f2f6978 |
| task-030-mmlu_astronomy:mc-predictions.jsonl | 236 kB | | 507bd35f |
| task-030-mmlu_astronomy:mc-recorded-inputs.jsonl | 33 kB | | 7fdd0909 |
| task-031-mmlu_college_biology:mc-metrics.json | 2.08 kB | | 91b0d9f1 |
| task-031-mmlu_college_biology:mc-predictions.jsonl | 223 kB | | 9b379e63 |
| task-031-mmlu_college_biology:mc-recorded-inputs.jsonl | 27.8 kB | | 11d574a8 |
| task-032-mmlu_college_chemistry:mc-metrics.json | 2.02 kB | | c944ac35 |
| task-032-mmlu_college_chemistry:mc-predictions.jsonl | 155 kB | | d35c3609 |
|