manipulation · benchmark suite
RLBench
Robot-learning benchmark and environment with 100 hand-designed tasks, variations, demonstrations, and multimodal observations.
verifiedAug 20, 2026Classification and metric are verified; maintenance recency is tracked separately.
Evaluation setting
simulation
Primary metric
Task success rate
Source count
3 bound primary sources
Provenance
Primary sources
Found an update or correction?
Submissions enter a private review queue and never change the public registry automatically.
Suggest a correction