Multi-task Language Understanding on MMLU (153-question shuffled subset)
87.28Accuracy
SIGMA
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 87.28 | |
2026.06 | 85.78 | |
2026.06 | 85.63 | |
2026.06 | 85.06 | |
2026.06 | 83.59 | |
2026.06 | 83.39 | |
2026.06 | 82.92 | |
2026.06 | 81.58 | |
2026.06 | 76.47 | |
2026.06 | 75.07 | |
2026.06 | 74.23 | |
2026.06 | 73.19 | |
2026.06 | 71.4 | |
2026.06 | 69.66 | |
2026.06 | 68.84 | |
2026.06 | 67.61 | |
2026.06 | 61.44 | |
2026.06 | 60.92 | |
2026.06 | 60.13 | |
2026.06 | 60.07 | |
2026.06 | 59.61 | |
2026.06 | 59.58 | |
2026.06 | 58.74 | |
2026.06 | 57.71 |