Long-context language modeling evaluation on RULER 32K
100S1 Score (RULER 32K)
SnapKV
Updated 25d ago
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
2026.03 | 100 | 85.8 | 89.8 | 13.6 | 7.25 | 16.5 | 20.88 | 62.77 | 45.8 | 49.16 | |
2026.03 | 100 | 80.6 | 78.8 | 14.4 | 3.69 | 5.05 | 20.48 | 60.27 | 44.6 | 45.31 | |
2026.03 | 100 | 90.6 | 92 | 44 | 24.8 | 56.5 | 20.92 | 64.27 | 50.8 | 60.43 | |
2026.03 | 100 | 95.2 | 96 | 38.4 | 31.05 | 64.35 | 21.6 | 65.8 | 51.4 | 62.64 | |
2026.03 | 99.6 | 98 | 98 | 97 | 46.6 | 94.15 | 22.28 | 69.78 | 53.2 | 75.4 | |
2026.03 | 98.4 | 85.6 | 92.4 | 8.4 | 7.75 | 17.1 | 21.24 | 66.47 | 51.2 | 49.84 | |
2026.03 | 0.8 | 0 | 0 | 0 | 0 | 0 | 4.04 | 24.2 | 23.6 | 5.85 |