Long-context retrieval and reasoning on RULER 1.0 (test)
83.2CWE
FullKV
Updated 2mo ago
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.05 | 83.2 | 99.33 | 100 | 100 | 100 | 100 | 98.5 | 100 | 100 | 100 | 86 | 64 | 100 | 94.69 | |
2026.05 | 64.5 | 97 | 100 | 100 | 99 | 100 | 92.75 | 100 | 100 | 100 | 71 | 63 | 99.8 | 91.31 | |
2026.05 | 60.6 | 96 | 100 | 14 | 2 | 100 | 98 | 100 | 100 | 4 | 34 | 48 | 97.2 | 65.67 | |
2026.05 | 57.8 | 92 | 8 | 10 | 2 | 16 | 0 | 16 | 0 | 4 | 32 | 46 | 28.4 | 24.02 |