Correctness Prediction on PIQA
80.69Accuracy
GRIFFIN
Updated 20d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.08 | 80.69 | |
2025.08 | 80.47 | |
2025.08 | 80.25 | |
2025.08 | 80.03 | |
2026.01 | 79.64 | |
2026.01 | 79.32 | |
2026.01 | 78.38 | |
2025.08 | 78.07 | |
2025.08 | 78.07 | |
2026.01 | 77.43 | |
2025.08 | 77.42 | |
2025.08 | 77.42 | |
2026.01 | 76.86 | |
2026.01 | 76.61 | |
2026.01 | 76.32 | |
2025.08 | 75.9 | |
2025.08 | 75.73 | |
2026.01 | 75.69 | |
2026.01 | 74.41 | |
2026.01 | 73.03 | |
2026.01 | 72.21 | |
2026.01 | 68.97 | |
2026.01 | 65.78 | |
2026.01 | 65.51 | |
2026.01 | 57.39 | |
2026.01 | 57.24 | |
2026.01 | 47.88 | |
2026.01 | 26.33 |