List your company

Question Answering on MuSiQue (F1, Acc, # Turn, AUC)

31.2F1 ScoreHybridDeepSearcher
12.06417.0322226.968Aug 26, 2025

Evaluation results

MethodLinks
HybridDeepSearcherSearch Strategy=Hybrid Search (Ours), Backbone=Qwen3-8B2025.0831.235.13.30.3
RAG-R1Search Strategy=Parallel Search, Backbone=Qwen2.5-7B-Instruct2025.0829.732.42.10.29
HybridDeepSearcherSearch Strategy=Hybrid Search (Ours), Backbone=Qwen2.5-7B-Instruct2025.0828.132.62.80.26
Search-R1Search Strategy=Sequential Search, Backbone=Qwen2.5-7B-Instruct2025.0826.629.13.20.23
R1-SearcherSearch Strategy=Sequential Search, Backbone=Qwen2.5-7B-Instruct2025.0825.128.52.70.24
Search-o1Search Strategy=Sequential Search, Backbone=Qwen3-8B2025.0823.431.83.70.26
DeepResearcherSearch Strategy=Parallel Search, Backbone=Qwen2.5-7B-Instruct2025.0821.723.43.40.19
Standard RAGSearch Strategy=Non-iterative, Backbone=Qwen3-8B2025.0815.824.8——
Naïve GenSearch Strategy=Non-iterative, Backbone=Qwen3-8B2025.0812.816.4——