Instruction Following on IFEval Inverse
83.7Inv-IF
Multi-DPOP
Updated 23d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 83.7 | - | |
2026.06 | 80.9 | - | |
2026.06 | 79.6 | - | |
2026.06 | 78.9 | - | |
2026.06 | 77.1 | - | |
2025.10 | 76.1 | - | |
2026.06 | 74.8 | - | |
2025.10 | 74.2 | - | |
2026.06 | 72.4 | - | |
2026.06 | 72.3 | - | |
2025.10 | 69.8 | - | |
2026.06 | 69.3 | - | |
2026.06 | 69.3 | - | |
2025.10 | 65.3 | - | |
2025.10 | 56.8 | - | |
2025.10 | 55.1 | - | |
2025.10 | 51.4 | - | |
2025.10 | 51.2 | - | |
2025.10 | 49.8 | - | |
2025.10 | 49.2 | - | |
2025.10 | 48.5 | - | |
2025.10 | 47.3 | - | |
2025.10 | 46.3 | - | |
2025.10 | 44.8 | - | |
2025.10 | 44.7 | - | |
2025.10 | 43.7 | - | |
2025.10 | 42.1 | - | |
2025.10 | 42.1 | - | |
2025.10 | 40.2 | - | |
2025.10 | 40.2 | - | |
2025.10 | 38.5 | - | |
2025.10 | 38.4 | - | |
2025.10 | 35.1 | - | |
2025.10 | 32.8 | - | |
2025.10 | - | 73.7 | |
2025.10 | - | 70.6 | |
2025.10 | - | 67.2 | |
2025.10 | - | 32.8 | |
2025.10 | - | 35.1 | |
2025.10 | - | 38.4 | |
2025.10 | - | 40.2 | |
2025.10 | - | 62.7 | |
2025.10 | - | 65.3 | |
2025.10 | - | 38.5 | |
2025.10 | - | 40.2 | |
2025.10 | - | 42.1 | |
2025.10 | - | 43.7 | |
2025.10 | - | 67.4 | |
2025.10 | - | 69.8 | |
2025.10 | - | 42.1 | |
2025.10 | - | 44.8 | |
2025.10 | - | 47.3 | |
2025.10 | - | 48.5 | |
2025.10 | - | 71.8 | |
2025.10 | - | 74.2 | |
2025.10 | - | 44.7 | |
2025.10 | - | 46.3 | |
2025.10 | - | 49.8 | |
2025.10 | - | 51.2 | |
2025.10 | - | 73.6 | |
2025.10 | - | 76.1 | |
2025.10 | - | 49.2 | |
2025.10 | - | 51.4 | |
2025.10 | - | 55.1 | |
2025.10 | - | 56.8 | |
2025.10 | - | 80.5 | |
2025.10 | - | 83.7 |