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

DomainBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Text GenerationDomainBench
BLEU (Agriculture)71.37
144
Instruction FollowingDomainBench
Agriculture Score21.85
80
Text GenerationDomainBench Finance
BERTScore0.7235
15
Text GenerationDomainBench Medicine
BERTScore0.701
7
Text GenerationDomainBench Agriculture
BERTScore0.6767
7
Text GenerationDomainBench Geography
BERTScore0.7082
7
Open-ended EvaluationDomainBench (test)
Geography Score27.98
7
Showing 7 of 7 rows