BEHAVIOR 2025 Challenge
Robotics challenge leaderboard for BEHAVIOR-1K household activity policies, ranked by Q-score and full-task success.
18rows
heldout_q_scoreprimary metric
2026-05-27sampled
Metadata
Metrics
Held-Out Q-Score, Public Validation Q-Score, Held-Out Full Task Success Rate, Public Validation Full Task Success Rate
| Rank | Subject | Held-Out Q-Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Robot Learning Collective | 0.2599 | — | Imported | 2026-05-27 |
| 2 | Comet | 0.2514 | — | Imported | 2026-05-27 |
| 3 | SimpleAI Robot | 0.1591 | — | Imported | 2026-05-27 |
| 4 | The North Star | 0.1204 | — | Imported | 2026-05-27 |
| 5 | Embodied Intelligence | 0.0947 | — | Imported | 2026-05-27 |
| 6 | RAPPER | 0.075 | — | Imported | 2026-05-27 |
| 7 | tobi | 0.0717 | — | Imported | 2026-05-27 |
| 8 | MR | 0.0512 | — | Imported | 2026-05-27 |
| 9 | RACL | 0.014 | — | Imported | 2026-05-27 |
| 10 | Ahri+EFFL+MLV | 0.01 | — | Imported | 2026-05-27 |
| 11 | Merlin Labs | 0.009 | — | Imported | 2026-05-27 |
| 12 | LYQRobotics | 0.008 | — | Imported | 2026-05-27 |
| 13 | ACT | 0.0037 | — | Imported | 2026-05-27 |
| 14 | StarVLA | 0.0019 | — | Imported | 2026-05-27 |
| 15 | Cloud-Data | 0 | — | Imported | 2026-05-27 |
| 16 | RobotSimArk | 0 | — | Imported | 2026-05-27 |
| 17 | EntropyMaximum | 0 | — | Imported | 2026-05-27 |
| 18 | Magikid | 0 | — | Imported | 2026-05-27 |
No matching rows.