Long-horizonOnline
CALVIN
Measures long-horizon, language-conditioned robot manipulation through sequences of continuous-control tasks.
AI Benchmark Index catalogs 3 long-horizon with source-linked metadata.
3 benchmarks
Long-horizonOnline
Measures long-horizon, language-conditioned robot manipulation through sequences of continuous-control tasks.
Long-horizonOnline
Tests long-horizon AI capabilities with a contamination-limited benchmark whose official site requires JavaScript.
Long-horizonOnline
Measures reliability across tasks with 25 to 100 dependent steps.
Published by AI Benchmark Index. How we check each benchmark.