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

ArchEHR-QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Clinical Question AnsweringArchEHR-QA 2026 (test)
ST113
8
Evidence AlignmentArchEHR-QA 2026 (test)
Overall Score81.5
8
Answer GenerationArchEHR-QA 2026 (test)
Overall Score36.3
6
Evidence IdentificationArchEHR-QA 2026 (test)
Overall Score63.7
6
Question InterpretationArchEHR-QA 2026 (test)
Overall Score31.2
5
Answer GenerationArchEHR-QA
SARI59.2
3
Question InterpretationArchEHR-QA
Overall Score31.2
3
AlignmentArchEHR-QA
Micro F181.5
2
Evidence ScoringArchEHR-QA
Strict Micro F163.7
2
Showing 9 of 9 rows