List your company

Open-domain Question Answering on HotpotQA in-domain

72.4F1 ScoreSearch-R1
-2.6370416.8437336.324555.80527Aug 8, 2025

Evaluation results

MethodLinks
Search-R1Model=Qwen-2.5-7B, Type=RAG-RL2025.0872.478.8
R1-SearcherModel=Qwen-2.5-7B, Type=RAG-RL2025.0871.878
UR2Model=Qwen-2.5-7B, Type=Our Implementations2025.0871.279.4
Vanilla RLModel=Qwen-2.5-7B, Type=Our Implementations2025.0870.978.8
R1-SearcherModel=LLaMA-3.1-8B, Type=RAG-RL2025.0870.876.8
UR2Model=LLaMA-3.1-8B, Type=Our Implementations2025.0870.178.8
Vanilla RLModel=LLaMA-3.1-8B, Type=Our Implementations2025.087077.6
UR2Model=Qwen-2.5-3B, Type=Our Implementations2025.0867.776
Vanilla RLModel=Qwen-2.5-3B, Type=Our Implementations2025.0865.973.6
Search-o1Model=GPT-4o-mini, Type=Advanced RAG2025.0864.373.4
Search-R1Model=Qwen-2.5-3B, Type=RAG-RL2025.0863.169.2
Standard RAGModel=GPT-4o-mini, Type=Vanilla Methods2025.0859.669.6
R1-Searcher++Model=Qwen-2.5-7B, Type=RAG-RL2025.085964.2
RATModel=GPT-4o-mini, Type=Advanced RAG2025.0853.859.2
Search-o1Model=LLaMA-3.1-8B, Type=Advanced RAG2025.085359.4
Search-o1Model=Qwen-2.5-7B, Type=Advanced RAG2025.0850.961.6
Standard RAGModel=Qwen-2.5-3B, Type=Vanilla Methods2025.0850.657
Standard RAGModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0849.262.8
Standard RAGModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.0847.554.4
CoTModel=GPT-4o-mini, Type=Vanilla Methods2025.0846.551.2
ZeroSearchModel=Qwen-2.5-7B, Type=RAG-RL2025.084650.4
Self-AskModel=GPT-4o-mini, Type=Advanced RAG2025.084550.4
RATModel=LLaMA-3.1-8B, Type=Advanced RAG2025.0844.548.8
Self-AskModel=LLaMA-3.1-8B, Type=Advanced RAG2025.084350.8
Zero-SearchModel=Qwen-2.5-3B, Type=RAG-RL2025.0842.745.8
RATModel=Qwen-2.5-7B, Type=Advanced RAG2025.0837.940.6
Search-o1Model=Qwen-2.5-3B, Type=Advanced RAG2025.0836.437.6
Self-AskModel=Qwen-2.5-3B, Type=Advanced RAG2025.0833.847.2
RATModel=Qwen-2.5-3B, Type=Advanced RAG2025.0830.132.2
Self-AskModel=Qwen-2.5-7B, Type=Advanced RAG2025.0828.861
CoTModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.0828.631.6
CoTModel=Qwen-2.5-3B, Type=Vanilla Methods2025.0826.627.2
CoTModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0824.931
Search-R1Backbone=Qwen-2.5-7B, Type=RAG-RL2025.080.7240.788
R1-SearcherBackbone=Qwen-2.5-7B, Type=RAG-RL2025.080.7180.78
UR2Backbone=Qwen-2.5-7B, Type=Our Implementations2025.080.7120.794
Vanilla RLBackbone=Qwen-2.5-7B, Type=Our Implementations2025.080.7090.788
R1-SearcherBackbone=LLaMA-3.1-8B, Type=RAG-RL2025.080.7080.768
UR2Backbone=LLaMA-3.1-8B, Type=Our Implementations2025.080.7010.788
Vanilla RLBackbone=LLaMA-3.1-8B, Type=Our Implementations2025.080.70.776
UR2Backbone=Qwen-2.5-3B, Type=Our Implementations2025.080.6770.76
Vanilla RLBackbone=Qwen-2.5-3B, Type=Our Implementations2025.080.6590.736
Self-AskBackbone=GPT-4.1-mini, Type=Advanced RAG2025.080.6540.75
Search-R1Backbone=Qwen-2.5-3B, Type=RAG-RL2025.080.6310.692
R1-Searcher++Backbone=Qwen-2.5-7B, Type=RAG-RL2025.080.590.642
RATBackbone=GPT-4.1-mini, Type=Advanced RAG2025.080.5690.642
Standard RAGBackbone=GPT-4.1-mini, Type=Vanilla Methods2025.080.5450.744
Search-o1Backbone=GPT-4.1-mini, Type=Advanced RAG2025.080.5310.74
Standard RAGBackbone=Qwen-2.5-3B, Type=Vanilla Methods2025.080.5060.57
Standard RAGBackbone=Qwen-2.5-7B, Type=Vanilla Methods2025.080.4920.628
Standard RAGBackbone=LLaMA-3.1-8B, Type=Vanilla Methods2025.080.4750.544
ZeroSearchBackbone=Qwen-2.5-7B, Type=RAG-RL2025.080.460.504
CoTBackbone=GPT-4.1-mini, Type=Vanilla Methods2025.080.4370.592
Zero-SearchBackbone=Qwen-2.5-3B, Type=RAG-RL2025.080.4270.458
CoTBackbone=LLaMA-3.1-8B, Type=Vanilla Methods2025.080.2860.316
CoTBackbone=Qwen-2.5-3B, Type=Vanilla Methods2025.080.2660.272
CoTBackbone=Qwen-2.5-7B, Type=Vanilla Methods2025.080.2490.31