Science Question Answering on GPQA D (Acc, #Tok, LR)
65.2Accuracy
CGRS
Updated 3d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.02 | 65.2 | 5,953 | 19.7 | |
2026.02 | 64.3 | 5,775 | 22.1 | |
2026.02 | 64.1 | 5,027 | 32.2 | |
2026.02 | 64 | 7,411 | - | |
2026.02 | 63.8 | 6,091 | 17.8 | |
2026.02 | 59.8 | 6,302 | 30.8 | |
2026.02 | 59.3 | 7,837 | 13.9 | |
2026.02 | 59.3 | 7,485 | 17.8 | |
2026.02 | 59.1 | 7,113 | 21.9 | |
2026.02 | 58.2 | 6,338 | 14.5 | |
2026.02 | 57.7 | 9,104 | - | |
2026.02 | 57.7 | 5,965 | 34.5 | |
2026.02 | 56.9 | 1,268 | 82.9 | |
2026.02 | 54.2 | 1,546 | 83 | |
2026.02 | 53 | 7,301 | - | |
2026.02 | 53 | 5,826 | 20.2 | |
2026.02 | 53 | 5,798 | 20.6 | |
2026.02 | 52.5 | 6,691 | 8.4 | |
2026.02 | 49.3 | 7,672 | - | |
2026.02 | 48.5 | 5,841 | 23.9 | |
2026.02 | 46.1 | 5,573 | 27.4 | |
2026.02 | 41.8 | 7,434 | 3.1 | |
2026.02 | 39.6 | 7,221 | 5.9 | |
2026.02 | 37.9 | 1,312 | 81.8 | |
2026.02 | 36.2 | 4,938 | 31.3 | |
2026.02 | 36.2 | 6,638 | 13.5 | |
2026.02 | 31.8 | 3,095 | 59.7 | |
2026.02 | 22.2 | 561 | 92.3 |