Long-context language understanding on RULER 32k context length
98.2VT Score
PQcache
Updated 3d ago
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 98.2 | - | - | - | - | 92.7 | 81 | 51 | 86.9 | 100 | 99 | - | - | - | |
2026.02 | 97.8 | - | - | - | - | 93 | 81 | 51 | 85.3 | 91 | 98 | - | - | - | |
2026.02 | 97.6 | - | - | - | - | 89.7 | 85 | 54 | 87.5 | 100 | 99 | - | - | - | |
2026.02 | 96.4 | - | - | - | - | 92.3 | 81 | 51 | 86.2 | 98 | 99 | - | - | - | |
2026.02 | 95.2 | - | - | - | - | 91.7 | 84 | 53 | 86.8 | 97 | 100 | - | - | - | |
2026.02 | 95.2 | - | - | - | - | 92.3 | 74 | 51 | 83.4 | 91 | 97 | - | - | - | |
2026.02 | 95 | - | - | - | - | 88.3 | 86 | 53 | 86.8 | 100 | 99 | - | - | - | |
2026.02 | 94.2 | - | - | - | - | 93.7 | 83 | 49 | 85.6 | 97 | 97 | - | - | - | |
2026.02 | 94.2 | - | - | - | - | 88.7 | 82 | 53 | 85.5 | 95 | 100 | - | - | - | |
2026.02 | 94.2 | - | - | - | - | 87.7 | 82 | 50 | 83.1 | 93 | 92 | - | - | - | |
2026.02 | 91.4 | - | - | - | - | 87.7 | 84 | 54 | 83.8 | 90 | 96 | - | - | - | |
2026.02 | 91.4 | - | - | - | - | 86 | 82 | 52 | 82.7 | 93 | 92 | - | - | - | |
2026.02 | 90.2 | - | - | - | - | 92.3 | 68 | 51 | 72 | 49 | 82 | - | - | - | |
2026.02 | 88.6 | - | - | - | - | 92.3 | 79 | 50 | 80.4 | 87 | 86 | - | - | - | |
2026.02 | 86 | - | - | - | - | 83.3 | 73 | 49 | 69.5 | 64 | 62 | - | - | - | |
2026.02 | 83.6 | - | - | - | - | 64 | 77 | 50 | 71.9 | 83 | 74 | - | - | - | |
2026.02 | 82.8 | - | - | - | - | 91.7 | 38 | 42 | 44.1 | 10 | 0 | - | - | - | |
2026.02 | 81 | - | - | - | - | 89.7 | 75 | 51 | 69.1 | 73 | 45 | - | - | - | |
2026.02 | 76 | - | - | - | - | 80 | 71 | 54 | 64.1 | 74 | 30 | - | - | - | |
2026.02 | 72.2 | - | - | - | - | 83.7 | 63 | 46 | 49.4 | 32 | 0 | - | - | - | |
2026.02 | 66.4 | - | - | - | - | 88.3 | 48 | 44 | 44.6 | 20 | 1 | - | - | - | |
2026.02 | 32.2 | - | - | - | - | 83 | 35 | 29 | 30.2 | 2 | 0 | - | - | - | |
2026.02 | 19.8 | 99.2 | 97.4 | 96.5 | 81.9 | 0 | 70.6 | 51.6 | 65.9 | - | - | - | - | - | |
2026.02 | 19.8 | 97.8 | 82 | 94.9 | 65.1 | 0 | 66.2 | 49.6 | 59.4 | - | - | - | - | - | |
2024.09 | 8.6 | - | - | - | - | 5 | - | - | - | - | - | 52.66 | 6.7 | 40.5 | |
2024.09 | 5.6 | - | - | - | - | 1.67 | - | - | - | - | - | 8.13 | 5.4 | 4 | |
2024.09 | 1.2 | - | - | - | - | 2 | - | - | - | - | - | 32.94 | 2.8 | 28.5 | |
2024.09 | 0.8 | - | - | - | - | 12.67 | - | - | - | - | - | 2.36 | 0.5 | 28 | |
2024.09 | 0.4 | - | - | - | - | 1.67 | - | - | - | - | - | 34.75 | 1.8 | 33.5 | |
2024.09 | 0.2 | - | - | - | - | 11.33 | - | - | - | - | - | 26.06 | 0.3 | 18.5 | |
2026.02 | 0 | - | - | - | - | 83 | 35 | 29 | 24.8 | 2 | 0 | - | - | - | |
2026.02 | 0 | - | - | - | - | 61.7 | 11 | 24 | 16.2 | 1 | 0 | - | - | - | |
2024.09 | 0 | - | - | - | - | 24 | - | - | - | - | - | 0.25 | 0.1 | 4.5 | |
2026.01 | - | - | - | - | - | - | - | - | 9.2 | - | - | - | - | - | |
2026.01 | - | - | - | - | - | - | - | - | 11.7 | - | - | - | - | - | |
2026.01 | - | - | - | - | - | - | - | - | 9.3 | - | - | - | - | - | |
2026.01 | - | - | - | - | - | - | - | - | 24.1 | - | - | - | - | - |