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

OVERNIGHT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Semantic ParsingOVERNIGHT v1.0 (test)
Blocks Domain Score65.7
26
Semantic ParsingOvernight Blk Few-shot 32 examples (test)
Program Acc74.4
8
Semantic ParsingOvernight Blk
Execution Acc97.2
4
Showing 3 of 3 rows