Out-of-Distribution Generalization on GPQA Diamond OOD
71.5Sav.
TTT no-QK
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 71.5 | 30 | |
2026.04 | 66.5 | 21 | |
2026.04 | 65.3 | 32.8 | |
2026.04 | 64.3 | 27 | |
2026.04 | 60.2 | 32.8 | |
2026.04 | 59.8 | 31.8 |
TTT no-QK
| Method | Links | ||
|---|---|---|---|
2026.04 | 71.5 | 30 | |
2026.04 | 66.5 | 21 | |
2026.04 | 65.3 | 32.8 | |
2026.04 | 64.3 | 27 | |
2026.04 | 60.2 | 32.8 | |
2026.04 | 59.8 | 31.8 |