New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
RoboTwin 2.0 benchmark
AI model leaderboard for the RoboTwin 2.0 benchmark. Compare how large language models score on RoboTwin 2.0, see the full ranking, and understand what this AI benchmark measures. Hy-Embodied-0.5-VLA currently leads with 90.9%. Bimanual robot-manipulation benchmark with domain randomization.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Hy-Embodied-0.5-VLA | Tencent Hunyuan | 90.9% | official ↗ |
Frequently asked questions about RoboTwin 2.0
What is the RoboTwin 2.0 benchmark?
Bimanual robot-manipulation benchmark with domain randomization.
How is the RoboTwin 2.0 benchmark scored?
RoboTwin 2.0 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 RoboTwin 2.0?
As of the latest reported scores on GenAIList, Hy-Embodied-0.5-VLA achieves the highest result on RoboTwin 2.0 with a score of 90.9%.
Is a higher RoboTwin 2.0 score better?
Yes. On RoboTwin 2.0 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.