Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AI2-iTHOR

Benchmarks

Task NameDataset NameSOTA ResultTrend
TRASHAI2-iTHOR environments (test)
Task Success Rate25
5
PREPAI2-iTHOR (test)
Task Success Rate33
5
SLICEAI2-iTHOR (test)
SLICE Task Success Rate36
5
CLEANAI2-iTHOR (test)
Task Success Rate53
5
HEATAI2-iTHOR (test)
Task Success Rate13
5
STOREAI2-iTHOR (test)
Task Success Rate0.12
5
COOLAI2-iTHOR (test)
Task Success Rate26
5
Showing 7 of 7 rows