New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
LIBERO benchmark
AI model leaderboard for the LIBERO benchmark. Compare how large language models score on LIBERO, see the full ranking, and understand what this AI benchmark measures. MolmoAct 2 currently leads with 98.1%. Lifelong robot-manipulation benchmark for VLA models.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | MolmoAct 2 | Allen Institute for AI | 98.1% | official ↗ | |
| #2 | Qwen-VLA | Qwen | 97.9% | official ↗ |
Frequently asked questions about LIBERO
What is the LIBERO benchmark?
Lifelong robot-manipulation benchmark for VLA models.
How is the LIBERO benchmark scored?
LIBERO is scored using the success rate (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on LIBERO?
As of the latest reported scores on GenAIList, MolmoAct 2 achieves the highest result on LIBERO with a score of 98.1%.
Is a higher LIBERO score better?
Yes. On LIBERO a higher score indicates better performance, so models near the top of the leaderboard are the strongest.