← Leaderboard
OpenVLA-OFT
VLAStanford · Feb 27, 2025 · built on OpenVLA
Optimized fine-tuning recipe for OpenVLA, adding parallel decoding, action chunking and continuous actions. Several RL post-training methods use it as their base.
- Type
- VLA
- Parameters
- 7B
- Backbone
- Prismatic (Llama 2 7B)
- Weights
- Open
- License
- MIT
- Commercial use
- Allowed
- Released
- Feb 27, 2025
- Robots
- Franka Panda (sim), ALOHA
- SO-101
- –
- LeRobot
- –
Benchmark results
3 of 13 benchmarksRoboDojo (sim)Simulation
- Paper / model card ↗Jul 2026
#40 of 400.0%, self-reported by the authors, not a leaderboard entry
LIBERO-PlusSimulation
- Paper / model card ↗Oct 2025
#19 of 2471.4%, self-reported by the authors, not a leaderboard entry
- Paper / model card ↗Feb 2025
#31 of 4697.1%, self-reported by the authors, not a leaderboard entry
Not reported on 10 benchmarks
Robustness drop: 97.1% on LIBERO → 71.4% 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 |
|---|---|---|---|---|---|---|---|---|
| A100 | – | parallel decoding + chunking + L1 regression, 1 image (LIBERO) | 72.9 ms | – | – | 8 | – | Feb 27, 2025 ↗ |
Trained on
Runs on
Wrong or missing number? Report an error