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

Home/Benchmarks

Multi-hop Question Answering on NQ Large-scale (train)

1.3Avg Search Steps

NQ

Updated 1mo ago

Evaluation Results

Method	Links
NQ 2026.01		1.3	83.1

SOTA Paper

NQ

SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback

Dataset

NQ

Follow for update

@wizwand_team Discord

Related Benchmarks

Multi-hop Question Answering on FRAMES (Accuracy)Multi-hop Question Answering on SAGE-generated In-domain (test)Deep Search on Browsecomp Multi-hop Question Answering on HotpotQA Large-scale (train)Multi-hop Question Answering on Musique Large-scale (train)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs