← Leaderboard
Cosmos Policy
World-actionNVIDIA · Jan 22, 2026
Robot policy fine-tuned from the Cosmos-Predict2 video model, reported on LIBERO, the classic 24-task RoboCasa and real ALOHA tasks.
- Type
- World-action
- Parameters
- 2B
- Backbone
- Cosmos-Predict2-2B
- Weights
- Open
- License
- NVIDIA One-Way Noncommercial License
- Commercial use
- Not allowed
- Released
- Jan 22, 2026
- Robots
- Franka Panda (sim), ALOHA
- SO-101
- –
- LeRobot
- –
Benchmark results
2 of 13 benchmarksLIBERO-PlusSimulation
- Paper / model card ↗Jun 2026
#12 of 2483.1%, self-reported by the authors, not a leaderboard entry
- Paper / model card ↗Jan 2026· n = 6000
#17 of 4698.5%, self-reported by the authors, not a leaderboard entry
Not reported on 11 benchmarks
Robustness drop: 98.5% on LIBERO → 83.1% on LIBERO-Plus. The perturbed variants show how much of the LIBERO score is memorization.
Adoption
updated Nov 17, 2026Running the model
| Hardware | Precision | Config | Latency / chunk | Steps | VRAM | Chunk | Control | Source |
|---|---|---|---|---|---|---|---|---|
| H100 | – | 1 denoising step (RoboCasa) | 160 ms | 1 | – | 32 | – | Jan 22, 2026 ↗ |
| unspecified | – | LIBERO sim | – | – | 6.8 GB | – | – | Jan 23, 2026 ↗ |
Trained on
Runs on
Wrong or missing number? Report an error