Reverse Chain-of-Thought Generation on IFEval
85.1Accuracy
SSR-D
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 85.1 | |
2026.02 | 84.8 | |
2026.02 | 84.5 | |
2026.02 | 83.8 | |
2026.02 | 83.7 | |
2026.02 | 83.4 | |
2026.02 | 83.2 | |
2026.02 | 82.9 | |
2026.02 | 81.6 | |
2026.02 | 81.5 | |
2026.02 | 81.2 | |
2026.02 | 80.1 | |
2026.02 | 80 | |
2026.02 | 78.5 | |
2026.02 | 78.2 | |
2026.02 | 77.6 | |
2026.02 | 77.2 | |
2026.02 | 76.7 | |
2026.02 | 76.5 | |
2026.02 | 74.3 |