Long-context Reasoning on BAMBOO 16k
41.5AltQA Score
DRIFT
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 41.5 | 80 | 77.78 | 60.15 | |
2026.02 | 40 | 75 | 76.77 | 57.89 | |
2026.02 | 40 | 75 | 76.77 | 57.89 | |
2026.02 | 37 | 81 | 84.85 | 59.9 | |
2026.02 | 36 | 82 | 82.83 | 59.15 | |
2026.02 | 36 | 77 | 78.79 | 56.89 | |
2026.02 | 36 | 78 | 82.83 | 58.15 | |
2026.02 | 34.5 | 79 | 75.76 | 55.89 | |
2026.02 | 30.5 | 60 | 47.47 | 42.11 | |
2026.02 | 25.5 | 49 | 41.41 | 35.34 | |
2026.02 | 25 | 68 | 57.58 | 43.86 | |
2026.02 | 21.5 | 19 | 19.19 | 20.3 | |
2026.02 | 15 | 40 | 36.36 | 26.57 |