Broad-Domain Factual and Professional Reasoning on MMLU PRO
0.711Accuracy (ACC)
Raw CoT
Updated 26d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 0.711 | 1,789 | |
2026.06 | 0.703 | 356 | |
2026.06 | 0.692 | 458 | |
2026.06 | 0.683 | 582 | |
2026.06 | 0.681 | 118 | |
2026.06 | 0.675 | 405 | |
2026.06 | 0.651 | 192 | |
2026.06 | 0.645 | 516 | |
2026.06 | 0.643 | 134 | |
2026.06 | 0.642 | 318 | |
2026.06 | 0.604 | 96 | |
2026.06 | 0.602 | 276 | |
2026.06 | 0.585 | 118 | |
2026.06 | 0.556 | 125 | |
2026.06 | 0.502 | 135 | |
2026.06 | 0.389 | 320 | |
2026.06 | 0.386 | 960 | |
2026.06 | 0.372 | 370 | |
2026.06 | 0.364 | 340 | |
2026.06 | 0.358 | 352 |