Science Question Answering on GPQA (test)
65.7Accuracy
ExpRAG
Updated 3d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 65.7 | - | - | |
| 65.7 | - | - | ||
2026.02 | 65.2 | - | - | |
2026.02 | 65.2 | - | - | |
2026.02 | 65.2 | - | - | |
2026.02 | 64.6 | - | - | |
2026.01 | 38.3 | 4.9 | 119 | |
2026.01 | 37.9 | 21.9 | 283.7 | |
2026.01 | 36.4 | 73.9 | 268.1 | |
2026.01 | 34.8 | 4.9 | 66.9 | |
2026.01 | 34.4 | 4.9 | 111.7 | |
2026.01 | 33.9 | 23.4 | 265.8 | |
2026.01 | 33.8 | 22.5 | 159.6 | |
2026.01 | 33 | 78.9 | 251.4 | |
| 32.8 | - | - | ||
2026.01 | 32.6 | 75.9 | 150.8 | |
2026.02 | 32.3 | - | - | |
2026.02 | 32.3 | - | - | |
2026.02 | 31.8 | - | - | |
2026.02 | 31.8 | - | - | |
2026.02 | 31.3 | - | - | |
2026.01 | 23.3 | 20.7 | 177.3 | |
2026.01 | 22.8 | 4.9 | 74.4 | |
2026.01 | 22.1 | 69.9 | 167.6 |