Spatio-temporal Reasoning on Spatio-temporal Reasoning Dataset Overall
87.5Frame F1 (F1f)
Q-SFT+RL
Updated 9d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 87.5 | 64.5 | 72.3 | |
2026.04 | 84.8 | 35 | 61 | |
2026.04 | 80.4 | 56.6 | 63.6 | |
2026.04 | 48.5 | 25 | 32.6 |
Q-SFT+RL
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 87.5 | 64.5 | 72.3 | |
2026.04 | 84.8 | 35 | 61 | |
2026.04 | 80.4 | 56.6 | 63.6 | |
2026.04 | 48.5 | 25 | 32.6 |