Language Understanding on MMLU o=1 (Semantic-level)
76.9Accuracy
W/O Decontamination
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 76.9 | 0.098 | |
2026.01 | 76.6 | 0.095 | |
2026.01 | 73.5 | 0.17 | |
2026.01 | 72.8 | 0.163 | |
2026.01 | 72.5 | 0.054 | |
2026.01 | 68.3 | 0.118 | |
2026.01 | 68.2 | 0.117 | |
2026.01 | 67.1 | - | |
2026.01 | 63.2 | 0.039 | |
2026.01 | 62.3 | 0.189 | |
2026.01 | 62 | 0.051 | |
2026.01 | 60.1 | 0.167 | |
2026.01 | 58.8 | 0.154 | |
2026.01 | 56.6 | 0.001 | |
2026.01 | 56.5 | - | |
2026.01 | 52.5 | 0.041 | |
2026.01 | 46.7 | 0.033 | |
2026.01 | 43.4 | - | |
2026.01 | 41.7 | 0.254 | |
2026.01 | 40.5 | 0.029 | |
2026.01 | 30.1 | 0.133 |