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

Multi-hop QA on Bamboogle (F1)

72F1 Score

Step-Level

Updated 9d ago

Evaluation Results

Method	Links
Step-Level 2026.05		72
Search-R1 2026.05		68
IRCoT 2026.05		65.7
Static RAG 2026.05		61.3