Knowledge Reasoning on MMLU 57 subjects (test)
74.3Accuracy
UTS-guided system
Updated 3mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 74.3 | 0.02 | 1.592 | |
2026.02 | 73.73 | 0.01 | 1.564 | |
2026.02 | 72.92 | 0.07 | 1.63 | |
2026.02 | 72.82 | 0.17 | 1.628 | |
2026.02 | 72.52 | 0.15 | 1.628 | |
2026.02 | 72.49 | 0.4 | 1.623 |