Long-horizon Task on Spatial and Temporal Simulation Tasks Step-level
3.909Subtask Accuracy
Cortex (full harness)
Updated 18d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.07 | 3.909 | 4.25 | 8.16 | |
2026.07 | 3.144 | 4.121 | 7.265 | |
2026.07 | 3.112 | 3.952 | 7.064 | |
2026.07 | 2.94 | 4.033 | 6.973 | |
2026.07 | 2.705 | 4.215 | 6.92 | |
2026.07 | 2.611 | 4.165 | 6.775 | |
2026.07 | 2.481 | 3.682 | 6.163 |