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

Hard Corpus

Benchmarks

Task NameDataset NameSOTA ResultTrend
Code GenerationHard Corpus 192 problems 4
Correctness (pass@1)83.3
12
Code GenerationHard Corpus 4 (192 problems)
S-opt75.5
4
Showing 2 of 2 rows