Question Answering on MMLU-Pro (full)
61Overall Accuracy (MMLU-Pro QA)
MTL
Updated 22d ago
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.05 | 61 | 81.6 | 67.5 | 67.5 | 65.1 | 70.3 | 52.2 | 57.2 | 50.4 | 35.4 | 71.3 | 51.3 | 53.3 | 65.7 | 69.9 | |
2026.05 | 59.4 | 75.1 | 66.8 | 64.4 | 64.2 | 68.6 | 47.6 | 58.2 | 42.6 | 27.3 | 77.5 | 47.7 | 46.6 | 63.4 | 63.5 | |
2026.05 | 58.3 | 75.2 | 65.7 | 63.8 | 63.5 | 67.8 | 47 | 57.5 | 42.1 | 27 | 76.5 | 47.2 | 46 | 62.6 | 63.1 | |
2026.05 | 58.1 | 74.3 | 66 | 63.6 | 63.4 | 67.8 | 46.8 | 57.3 | 41.7 | 26.3 | 76.7 | 46.9 | 45.7 | 62.6 | 62.7 | |
2026.05 | 57.3 | 72.7 | 64.7 | 62.3 | 62.2 | 66.3 | 46.1 | 56.3 | 41.2 | 26.4 | 75 | 46.2 | 45.1 | 61.4 | 61.4 | |
2026.05 | 55.4 | 75.6 | 62.9 | 57.9 | 61.5 | 64.5 | 47.8 | 53.3 | 42.5 | 25.2 | 69.2 | 46.5 | 45.1 | 57.8 | 62.9 | |
2026.05 | 54.7 | 72.1 | 59.4 | 57.4 | 58.8 | 64.5 | 41.2 | 53.3 | 40.4 | 24.7 | 71 | 46.7 | 45.7 | 59.3 | 63.5 | |
2026.05 | 51.6 | 73.8 | 57 | 49.3 | 51.9 | 61.4 | 44.7 | 50 | 41.5 | 24.6 | 62.7 | 43.4 | 44.5 | 53.7 | 63 | |
2026.05 | 27.5 | 42.1 | 33.3 | 19.9 | 30 | 35.2 | 21.1 | 22.3 | 18.6 | 14.7 | 36.1 | 22.5 | 22.7 | 28.9 | 37.1 | |
2026.05 | 27.1 | 38.9 | 29.1 | 23.8 | 28.3 | 34.9 | 22 | 21.1 | 15.2 | 14.3 | 40 | 22.2 | 21.2 | 26.4 | 35.1 | |
2026.05 | 26.8 | 42.3 | 33 | 18.9 | 29.5 | 35 | 20.1 | 21.4 | 17.6 | 13.5 | 35.9 | 21.6 | 21.8 | 28.4 | 36.9 | |
2026.05 | 26.5 | 42.2 | 32.7 | 18.3 | 29.2 | 34.7 | 19.6 | 20.9 | 17 | 12.8 | 35.7 | 21.1 | 21.3 | 28 | 36.8 | |
2026.05 | 26.2 | 41.2 | 32.2 | 18.4 | 28.7 | 34.1 | 19.6 | 20.8 | 17.1 | 13.1 | 35 | 21.1 | 21.2 | 27.7 | 36 | |
2026.05 | 24.9 | 36.7 | 30.9 | 22.4 | 23.9 | 27.8 | 19.2 | 21 | 16.5 | 12.9 | 35.9 | 21.1 | 18 | 25.9 | 28.4 | |
2026.05 | 24.7 | 36.3 | 28.4 | 21.7 | 22.9 | 30.9 | 19.7 | 19.7 | 15.8 | 11.5 | 36.3 | 19.8 | 20 | 26.4 | 29.6 | |
2026.05 | 24.4 | 33.9 | 28.1 | 20.6 | 22.9 | 29 | 17.3 | 23.5 | 18.9 | 14.4 | 33.2 | 21.4 | 17.2 | 23.4 | 34.3 |