Out-of-Distribution Generalization on AIME '26
19.8Saving Score
TTT no-QK
Updated 16d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 19.8 | 5 | |
2026.04 | 15.4 | 6.7 | |
2026.04 | 14.7 | 5 | |
2026.04 | 14.7 | 10 | |
2026.04 | 13.4 | 5 | |
2026.04 | 9.2 | 0 |
TTT no-QK
| Method | Links | ||
|---|---|---|---|
2026.04 | 19.8 | 5 | |
2026.04 | 15.4 | 6.7 | |
2026.04 | 14.7 | 5 | |
2026.04 | 14.7 | 10 | |
2026.04 | 13.4 | 5 | |
2026.04 | 9.2 | 0 |