Out-of-Distribution Generalization on AIME'24
29.5Saving Score
TTT QK (dh=128)
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 29.5 | 10 | |
2026.04 | 29.3 | 15 | |
2026.04 | 18.5 | 3.3 | |
2026.04 | 15.8 | 5 | |
2026.04 | 14.1 | 3.3 | |
2026.04 | 11.8 | 3.3 |
TTT QK (dh=128)
| Method | Links | ||
|---|---|---|---|
2026.04 | 29.5 | 10 | |
2026.04 | 29.3 | 15 | |
2026.04 | 18.5 | 3.3 | |
2026.04 | 15.8 | 5 | |
2026.04 | 14.1 | 3.3 | |
2026.04 | 11.8 | 3.3 |