Factual knowledge on Include Lite
41.88Seen Accuracy
GRPO
Updated 8d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 41.88 | 37.62 | 38.98 | |
2026.05 | 41.67 | 37.71 | 38.97 | |
2026.05 | 41.38 | 37.69 | 38.87 | |
2026.05 | 41.1 | 37.18 | 38.43 | |
2026.05 | 41.05 | 37.41 | 38.56 | |
2026.05 | 40.94 | 37.35 | 38.49 | |
2026.05 | 40.58 | 37.51 | 38.49 | |
2026.05 | 37.16 | 28.9 | 31.52 | |
2026.05 | 36 | 29.18 | 31.35 | |
2026.05 | 35.91 | 28.84 | 31.09 | |
2026.05 | 35.62 | 29.1 | 31.17 | |
2026.05 | 35.57 | 28.82 | 30.97 | |
2026.05 | 35.37 | 28.92 | 30.97 | |
2026.05 | 35.06 | 28.66 | 30.69 | |
2026.05 | 29.67 | 27.47 | 28.17 | |
2026.05 | 29.66 | 27.14 | 27.94 | |
2026.05 | 29.59 | 27.03 | 27.84 | |
2026.05 | 29.57 | 27.22 | 27.97 | |
2026.05 | 29.52 | 27.52 | 28.16 | |
2026.05 | 29.3 | 27.18 | 27.86 | |
2026.05 | 29.28 | 27.17 | 27.84 |