Open-ended generation on MMLU-Redux
4.22FDR (%)
FDR search
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.10 | 4.22 | 29.87 | 25.11 | - | |
2025.10 | 4.84 | 33.62 | 28.46 | - | |
2025.10 | 4.92 | 29.19 | 26.34 | - | |
2025.10 | 4.95 | 24.64 | 21.46 | - | |
2025.10 | 5.8 | 27.48 | 24.7 | - | |
2025.10 | 5.85 | 23.77 | 20.62 | - | |
2025.10 | 42.56 | 4.08 | 3.61 | - | |
2025.10 | 43.17 | 9.06 | 7.71 | - | |
2025.10 | 51.35 | 6.89 | 6.3 | - | |
2025.10 | - | - | - | 20.17 | |
2025.10 | - | - | - | 20.79 | |
2025.10 | - | - | - | 15.07 |