manipulation · benchmark suite
CALVIN
Simulated benchmark, environment, dataset, and challenge for long-horizon language-conditioned control.
potentially staleAug 20, 2026The official project site failed retrieval on 2026-08-20 and the official repository reports dataset/site connection failures. Reverify availability and checksum before publication.
Evaluation setting
simulation
Primary metric
No single standardized metric
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