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

Evidence Sufficiency Verification on HotpotQA RAG v3

89.51Macro-F1

SURE-RAG

72.173276.674181.17585.6759May 5, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
89.51
2026.05
72.84