Language Understanding on MMLU-Pro (Subject Accuracy Breakdown)
68.6Overall Accuracy (MMLU-Pro)
MTL
Updated 22d ago
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.05 | 68.6 | 86.2 | 74 | 72.4 | 67.8 | 77 | 56.8 | 67.3 | 61.9 | 39.9 | 79.4 | 64.6 | 61.7 | 72.2 | 77.6 | |
2026.05 | 67.8 | 83.8 | 73.1 | 72.3 | 72.7 | 76.2 | 55.8 | 66.1 | 59.6 | 36.1 | 83.4 | 61.5 | 59.5 | 73.3 | 72.3 | |
2026.05 | 66.6 | 83.7 | 71.8 | 70.2 | 65.8 | 74.7 | 55.1 | 65.3 | 60.1 | 38.7 | 77 | 62.7 | 59.9 | 70.1 | 75.3 | |
2026.05 | 66.5 | 84.4 | 72.1 | 67.1 | 69.5 | 74.6 | 56.4 | 66.6 | 57.5 | 35.4 | 80.5 | 61.8 | 58.7 | 69.7 | 74.3 | |
2026.05 | 66.4 | 83.9 | 71.7 | 70.1 | 65.6 | 74.7 | 54.6 | 65 | 59.7 | 37.7 | 77.1 | 62.4 | 59.5 | 70 | 75.3 | |
2026.05 | 65.6 | 82.7 | 70.8 | 69.2 | 64.8 | 73.7 | 54.1 | 64.3 | 59.1 | 37.7 | 76 | 61.7 | 58.9 | 69.1 | 74.3 | |
2026.05 | 65.3 | 83.3 | 70.6 | 65.9 | 66.3 | 74.4 | 54.3 | 65.4 | 58 | 40.2 | 76.1 | 58.2 | 60.7 | 67.5 | 73.9 | |
2026.05 | 65.3 | 84.2 | 70 | 67 | 63.4 | 74.1 | 52.6 | 66.3 | 59.3 | 33.5 | 80.9 | 61.2 | 55.9 | 69.1 | 71.7 | |
2026.05 | 63.7 | 81.4 | 68.9 | 64.2 | 64.7 | 72.7 | 52.7 | 63.7 | 56.4 | 38.8 | 74.3 | 56.6 | 59.1 | 65.8 | 72.2 | |
2026.05 | 62.9 | 78.1 | 69.1 | 67.9 | 65.1 | 71.3 | 53 | 62.4 | 52 | 32.1 | 78.7 | 55.5 | 51.9 | 67.4 | 67.9 | |
2026.05 | 62.4 | 79.4 | 68.3 | 67 | 65.4 | 70.5 | 52.6 | 61.5 | 51.7 | 32.3 | 77.3 | 55.5 | 52.1 | 66 | 67.4 | |
2026.05 | 61.9 | 78.8 | 66.8 | 62.4 | 62.8 | 70.5 | 51.4 | 61.9 | 54.9 | 38.1 | 72 | 55.1 | 57.5 | 63.9 | 70 | |
2026.05 | 60.4 | 78.8 | 66.2 | 63 | 61 | 71.1 | 51.8 | 59.4 | 49.9 | 29.9 | 72.3 | 52.9 | 55.3 | 63.2 | 68.2 | |
2026.05 | 60.4 | 79.6 | 63.4 | 59.5 | 63.4 | 73.3 | 48.1 | 61.9 | 53.8 | 34.4 | 68.6 | 58.2 | 56.1 | 58.6 | 72.6 | |
2026.05 | 59.6 | 79.4 | 63.5 | 59.6 | 61.5 | 69.8 | 48.9 | 62 | 50.4 | 29.9 | 71.3 | 54.6 | 51.9 | 62.5 | 68.5 | |
2026.05 | 55.2 | 75.2 | 59.2 | 53.7 | 51.7 | 67.1 | 48.4 | 54.4 | 49.9 | 27.3 | 59.1 | 51.5 | 51.7 | 57 | 67.2 | |
2026.05 | 44.4 | 65.1 | 51.6 | 43 | 47.3 | 52.3 | 37.1 | 41.9 | 30.2 | 23.3 | 53.2 | 35.8 | 39.5 | 46.4 | 52.9 | |
2026.05 | 43.5 | 64.9 | 51 | 42.2 | 46.6 | 51.7 | 36.1 | 41.1 | 29 | 21.9 | 52.7 | 34.8 | 38.6 | 45.7 | 52.3 | |
2026.05 | 41.8 | 60.7 | 49.7 | 41.4 | 45.9 | 50.8 | 36.6 | 36.9 | 24.4 | 18.4 | 56.4 | 34.4 | 32.3 | 42.3 | 47.5 | |
2026.05 | 41.7 | 62.7 | 49 | 40.4 | 44.8 | 49.7 | 34.5 | 39.3 | 27.5 | 20.5 | 50.7 | 33.1 | 36.8 | 43.8 | 50.4 | |
2026.05 | 41.1 | 61.4 | 48.2 | 39.9 | 44 | 48.8 | 34.2 | 38.8 | 27.4 | 20.6 | 49.8 | 32.9 | 36.4 | 43.2 | 49.5 | |
2026.05 | 40 | 58.2 | 44.6 | 39.6 | 40 | 48.6 | 32.3 | 35.8 | 24.1 | 17.7 | 55.4 | 31.7 | 31.5 | 42.9 | 46.6 | |
2026.05 | 38.5 | 58.2 | 42.2 | 37.6 | 41.2 | 46.3 | 28 | 35.4 | 27.3 | 16.2 | 50.8 | 33.1 | 30.9 | 40.5 | 47.4 | |
2026.05 | 36.8 | 55.6 | 39.7 | 36.3 | 37.6 | 48 | 29 | 31.9 | 24.9 | 17.7 | 47.1 | 31.2 | 32.1 | 36.6 | 47.4 |