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

MTSamples

Benchmarks

Task NameDataset NameSOTA ResultTrend
Relation ExtractionMTSamples (test)
Strict F1 Score83.1
26
Named Entity RecognitionMTSamples (test)
Strict F187
26
Named Entity RecognitionMTSamples
Precision91.5
14
Clinical NLP TasksMTSamples
GPT-4 Score3.64
10
Medical Text ClassificationMTSamples held-out (test)
Macro F1 Score27.9
7
Showing 5 of 5 rows