Scientific Reasoning on GPQA (Accuracy, Speed)
63Accuracy
SR
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 63 | 1.09 | |
2026.06 | 62 | 1 | |
2026.06 | 62 | 1.12 | |
2026.06 | 61 | 0.78 | |
2026.06 | 61 | 1.76 | |
2026.06 | 60 | 2.18 | |
2026.06 | 60 | 1.7 | |
2026.06 | 60 | 1.81 | |
2026.06 | 60 | 1.94 | |
2026.06 | 58 | 1 | |
2026.06 | 58 | 0.57 | |
2026.06 | 57 | 1.98 | |
2026.06 | 56 | 0.61 | |
2026.06 | 55 | 1.38 | |
2026.06 | 55 | 1.07 | |
2026.06 | 55 | 0.82 | |
2026.06 | 54 | 1.16 | |
2026.06 | 53 | 2.14 | |
2026.06 | 53 | 2.21 | |
2026.06 | 52 | 2.06 | |
2026.06 | 45 | 4.53 | |
2026.06 | 22 | 6.42 |