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

SO-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Complex Reasoning and SemanticsSO-Bench
CM Score45.16
16
Spatial Relation UnderstandingSO-Bench
IS-DoA64.26
16
Basic Detection and EstimationSO-Bench
DS Score53.97
16
Showing 3 of 3 rows