Long-context language understanding on RULER 64k context length
63.8QA Score
CLAA
Updated 3d ago
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 63.8 | - | 87.72 | 86.67 | - | - | - | - | - | 82.01 | 89.85 | - | - | |
2026.02 | 63.7 | - | 58.2 | 88.33 | - | - | - | - | - | 73.12 | 82.23 | - | - | |
2026.02 | 63.6 | - | 87.16 | 86.67 | - | - | - | - | - | 81.28 | 87.69 | - | - | |
2026.02 | 63.3 | - | 86.88 | 86.67 | - | - | - | - | - | 83.78 | 98.27 | - | - | |
2024.09 | 34.5 | - | - | - | - | 6.2 | 32.67 | - | - | - | - | 9.34 | 0.2 | |
2024.09 | 29.5 | - | - | - | - | 0.6 | 6.33 | - | - | - | - | 2.63 | 4.9 | |
2024.09 | 15 | - | - | - | - | 0.2 | 13.33 | - | - | - | - | 23.25 | 0.3 | |
2024.09 | 9 | - | - | - | - | 0 | 15.67 | - | - | - | - | 0.31 | 2.4 | |
2024.09 | 1 | - | - | - | - | 4.4 | 10.67 | - | - | - | - | 50.13 | 2.6 | |
2026.02 | - | 99.4 | 98.4 | 96.8 | 93.7 | 19.8 | 0 | 70.4 | 47.6 | 65.8 | - | - | - | |
2026.02 | - | 99.6 | 73.2 | 90.3 | 81.7 | 19.9 | 0 | 63.4 | 44.4 | 59 | - | - | - |