List your company

Question Answering on MuSiQue in-domain (test)

33.47LasJD2PLAN-7B
9.373215.629121.88528.1409Jan 13, 2026

Evaluation results

MethodLinks
D2PLAN-7BBase LLM=Qwen2.5-7B-Instruct2026.0133.4724.41
D2PLAN-3BBase LLM=Qwen2.5-3B-Instruct2026.0133.1423.13
R1-SearcherBase LLM=Qwen2.5-7B-Instruct2026.0129.8321.93
ReSearchBase LLM=Qwen2.5-7B-Instruct2026.0129.8321.43
StepSearchBase LLM=Qwen2.5-7B-Instruct2026.0128.5520.31
AutoRefineBase LLM=Qwen2.5-3B-Instruct2026.0128.2619.49
Search-R1Base LLM=Qwen2.5-7B-Instruct2026.0121.5115.27
Search-R1Base LLM=Qwen2.5-3B-Instruct2026.0116.016.25
ZeroSearchBase LLM=Qwen2.5-7B-Instruct2026.0114.239.39
StepSearchBase LLM=Qwen2.5-3B-Instruct2026.0113.248.52
ZeroSearchBase LLM=Qwen2.5-3B-Instruct2026.0110.36