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

LEGO-Puzzles

Benchmarks

Task NameDataset NameSOTA ResultTrend
Compositional ReasoningLego Puzzles
Accuracy57.7
13
Procedural assembly reasoningLEGO-Puzzles
Height Accuracy52
12
Procedural Temporal UnderstandingLEGO-Puzzles (test)
Overall Accuracy42.82
7
Showing 3 of 3 rows