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

polyglot

Benchmarks

Task NameDataset NameSOTA ResultTrend
Named Entity Recognitionpolyglot-NER
Entity F175.65
16
Code GenerationPolyglot full-benchmark
Pass Rate30.7
4
CodingPolyglot n=166 (held-out)
Pass Count119
3
Code GenerationPolyglot 50-task staged
Pass Rate38
2
Showing 4 of 4 rows