Scientific QA on GPQA-Diamond
99.3Final Accuracy
Base
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 99.3 | 90.4 | 90.6 | |
2026.01 | 98.9 | 89.2 | 89.3 | |
2026.01 | 96.9 | 85.9 | 85.8 | |
2026.01 | 95.7 | 90 | 90.6 | |
2026.01 | 70.3 | 63.7 | 63.8 | |
2026.01 | 69.8 | 63.5 | 63.5 | |
2026.01 | 69.7 | 64.3 | 64.4 | |
2026.01 | 69.4 | 66.2 | 66.2 | |
2026.01 | 69.4 | 66.2 | 67.1 | |
2026.01 | 69.3 | 63.4 | 63.4 | |
2026.01 | 65.3 | 54.8 | 54.9 | |
2026.01 | 60.7 | 56.4 | 60.7 | |
2026.01 | 59 | 52.4 | 53 | |
2026.01 | 56.4 | 52 | 53.1 | |
2026.01 | 52.9 | 57.2 | 62.3 | |
2026.01 | 52.8 | 53 | 54.7 | |
2026.01 | 50.9 | 57.7 | 61.7 | |
2026.01 | 50.6 | 54.4 | 62.5 | |
2026.01 | 48.1 | 47.9 | 52.4 | |
2026.01 | 47.7 | 58.2 | 63.7 | |
2026.01 | 45.4 | 47.3 | 52.8 | |
2026.01 | 44.3 | 51.5 | 63.8 | |
2026.01 | 42.8 | 44.7 | 52 | |
2026.01 | 39.3 | 46.4 | 52.5 | |
2026.01 | 36.8 | 47.9 | 63.6 | |
2026.01 | 34.2 | 47.3 | 58.2 | |
2026.01 | 28.4 | 43.5 | 58.2 | |
2026.01 | 21 | 36.8 | 56.7 |