Long-context Question Answering on L-Eval QA
80.73NQ
DRIFT
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 80.73 | 27.1 | 76.16 | 55.96 | |
2026.02 | 80.73 | 33.18 | 75.58 | 58.38 | |
2026.02 | 79.82 | 31.78 | 65.12 | 53.94 | |
2026.02 | 77.98 | 33.18 | 64.53 | 53.94 | |
2026.02 | 72.48 | 21.5 | 63.37 | 47.27 | |
2026.02 | 71.56 | 17.29 | 60.47 | 44.24 | |
2026.02 | 70.64 | 24.77 | 58.72 | 46.67 | |
2026.02 | 69.72 | 27.1 | 61.05 | 48.28 | |
2026.02 | 61.47 | 9.81 | 53.49 | 36.36 | |
2026.02 | 56.88 | 12.62 | 50.58 | 35.56 | |
2026.02 | 53.21 | 8.88 | 55.81 | 34.95 | |
2026.02 | 40.37 | 5.61 | 39.53 | 25.05 | |
2026.02 | 36.7 | 5.14 | 15.7 | 15.76 |