Science Reasoning on GPQA (test)
64.44Accuracy
InjectRLOpt
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 64.44 | |
2026.02 | 63.33 | |
2026.02 | 62.32 | |
2026.02 | 60.61 | |
2026.02 | 60.51 | |
2026.02 | 60.4 | |
2026.02 | 59.49 | |
2026.02 | 58.69 | |
2026.02 | 57.07 | |
2026.02 | 54.14 | |
2026.02 | 53.23 | |
2026.02 | 52.22 | |
2024.05 | 37.8 | |
2024.05 | 36.8 | |
2024.05 | 36.8 | |
2025.04 | 34.82 | |
2024.05 | 31.8 | |
2025.04 | 30.35 | |
2025.04 | 30.13 | |
2025.04 | 29.91 | |
2025.04 | 29.69 | |
2025.04 | 28.79 | |
2025.04 | 28.57 | |
2025.04 | 28.57 | |
2025.04 | 28.35 | |
2025.04 | 28.13 | |
2025.04 | 26.79 | |
2025.04 | 26.56 | |
2025.04 | 23.44 | |
2025.04 | 22.99 | |
2026.01 | 21.68 | |
2026.01 | 20.54 | |
2025.04 | 20.31 | |
2026.01 | 17.95 | |
2026.01 | 16.84 | |
2026.01 | 16.13 | |
2026.01 | 15.14 | |
2026.01 | 14.73 | |
2026.01 | 14.54 | |
2026.01 | 13.96 | |
2026.01 | 13.66 |