Multi-turn Dialogue on Spec-Bench Multi.
3.22CR
SpecBound
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 3.22 | 1.69 | |
2026.04 | 3.05 | 1.65 | |
2026.04 | 2.74 | 1.66 | |
2026.04 | 2.69 | 1.85 | |
2026.04 | 2.44 | 1.66 | |
2026.04 | 2.31 | 1.71 | |
2026.04 | 2.22 | 1.68 | |
2026.04 | 2.2 | 1.52 | |
2026.04 | 2.07 | 1.67 | |
2026.04 | 2.04 | 1.65 | |
2026.04 | 2 | 1.4 | |
2026.04 | 1.94 | 1.5 | |
2026.04 | 1.91 | 1.48 | |
2026.04 | 1.89 | 2.09 | |
2026.04 | 1.86 | 2.07 | |
2026.04 | 1.78 | 1.51 | |
2026.04 | 1.74 | 1.49 | |
2026.04 | 1.72 | 1.95 | |
2026.04 | 1.68 | 1.92 | |
2026.04 | 1.64 | 1.41 | |
2026.04 | 1.61 | 1.39 |