Model card
OpenVLA.
Stanford / Google DeepMind / TRIopen-source7B vision-language-action model based on Llama-2 + fused DINOv2/SigLIP vision encoders
Kim et al. 2024. Open-source VLA model fine-tuned on Open X-Embodiment data.
§ 02 · Benchmarks
Every benchmark OpenVLA has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LIBERO-Long | Robots · Robot Manipulation | success-rate | 76.5% | #5 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 04 · Papers
1 paper with results for OpenVLA.
- 2024-06-13· 1 result
OpenVLA: An Open-Source Vision-Language-Action Model
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
1
result
0 of 1 rows marked verified.