List your company

Question Answering on HotpotQA in-domain (test)

61.59LASJD2PLAN-7B
32.36639.95347.5455.127Jan 13, 2026

Evaluation results

MethodLinks
D2PLAN-7BBase LLM=Qwen2.5-7B-Instruct2026.0161.5946.17
R1-SearcherBase LLM=Qwen2.5-7B-Instruct2026.0159.0344.32
D2PLAN-3BBase LLM=Qwen2.5-3B-Instruct2026.0157.9343.58
ReSearchBase LLM=Qwen2.5-7B-Instruct2026.0157.6242.5
AutoRefineBase LLM=Qwen2.5-3B-Instruct2026.0157.4141.12
StepSearchBase LLM=Qwen2.5-7B-Instruct2026.0152.7838.93
Search-R1Base LLM=Qwen2.5-7B-Instruct2026.0151.6737.31
ZeroSearchBase LLM=Qwen2.5-7B-Instruct2026.0145.2533.48
ZeroSearchBase LLM=Qwen2.5-3B-Instruct2026.0140.6129.44
StepSearchBase LLM=Qwen2.5-3B-Instruct2026.0137.3126.64
Search-R1Base LLM=Qwen2.5-3B-Instruct2026.0133.4918.07