Unified evaluation results for Vision-Language-Action models across robot simulation benchmarks
🤖 This leaderboard is largely maintained by AI to keep pace with the growing number of VLA papers.
Errors are possible — community corrections keep it accurate. Report an issue →
Evaluation protocols are not fully standardized across all benchmarks — scores may not always be directly comparable.
We welcome contributions: corrections, missing results, and protocol clarifications.
Contributing guide →