Out-of-Distribution Generalization on MATH-500 OOD (test)
67Score (Sav.)
TTT QK (dh=128)
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 67 | 2.1 | |
2026.04 | 63.7 | 2.3 | |
2026.04 | 63.7 | 1.6 | |
2026.04 | 55.5 | 1.2 | |
2026.04 | 24.8 | 0.8 | |
2026.04 | 23.9 | 0.4 |
TTT QK (dh=128)
| Method | Links | ||
|---|---|---|---|
2026.04 | 67 | 2.1 | |
2026.04 | 63.7 | 2.3 | |
2026.04 | 63.7 | 1.6 | |
2026.04 | 55.5 | 1.2 | |
2026.04 | 24.8 | 0.8 | |
2026.04 | 23.9 | 0.4 |