Long-context Question Answering on ∞Bench
78.46Accuracy
StateLM-14B-RL
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 78.46 | - | - | |
2026.02 | 77.44 | - | - | |
2026.02 | 74.96 | - | - | |
2026.02 | 74.24 | - | - | |
2026.02 | 73.36 | - | - | |
2026.02 | 73.07 | - | - | |
2026.02 | 70.16 | - | - | |
2026.02 | 67.25 | - | - | |
2026.02 | 66.81 | - | - | |
2026.02 | 62.45 | - | - | |
2026.02 | 59.97 | - | - | |
2026.02 | 34.06 | - | - | |
2026.02 | 24.02 | - | - | |
2026.02 | - | 1.76 | 2.18 | |
2026.02 | - | 3.7 | 4.05 | |
2026.02 | - | 6 | 8.5 | |
2026.02 | - | 8.53 | 12.54 |