List your company

Single-hop Question Answering on NQ (Natural Questions) (test)

45.3AccuracyInfoReasoner-3B
3.1814.11525.0535.985Jan 31, 2026

Evaluation results

MethodLinks
InfoReasoner-3BRetrieval=true, Model Scale=3B2026.0145.3
InfoReasoner-7BRetrieval=true, Model Scale=7B2026.0144.7
AutoRefine-7B-BaseRetrieval=true, Model Scale=7B2026.0143.9
Search-R1-7B-InstructRetrieval=true, Model Scale=7B2026.0140.7
Search-R1-3B-InstructRetrieval=true, Model Scale=3B2026.0140.5
Search-R1-3B-BaseRetrieval=true, Model Scale=3B2026.0139.4
Search-R1-7B-BaseRetrieval=true, Model Scale=7B2026.0139.1
InForge-3BRetrieval=true, Model Scale=3B2026.0138.6
AutoRefine-3B-InstructRetrieval=true, Model Scale=3B2026.0138.3
RAGRetrieval=true, Model Scale=3B2026.0134.8
ReSearch-7B-InstructRetrieval=true, Model Scale=7B2026.0133.3
ReasonRAG-7BRetrieval=true, Model Scale=7B2026.0129.4
AutoRefine-3B-BaseRetrieval=true, Model Scale=3B2026.0128.1
ReSearch-7B-BaseRetrieval=true, Model Scale=7B2026.0126.8
SFTRetrieval=false, Model Scale=3B2026.0124.9
Search-o1Retrieval=true, Model Scale=3B2026.0123.8
R1-BaseRetrieval=false, Model Scale=3B2026.0122.6
R1-InstructRetrieval=false, Model Scale=3B2026.0121
IRCoTRetrieval=true, Model Scale=3B2026.0111.1
Direct GenerationRetrieval=false, Model Scale=3B2026.0110.6
CoTRetrieval=false, Model Scale=3B2026.014.8