List your company

Open-domain QA on Bambogle v1 (out-of-domain)

64.7F1 ScoreR1-Searcher
24.55634.97845.455.822Aug 8, 2025

Evaluation results

MethodLinks
R1-SearcherModel=LLaMA-3.1-8B, Type=RAG-RL2025.0864.762.4
UR2Model=Qwen-2.5-7B, Type=Our Implementations2025.0864.562.4
Vanilla RLModel=Qwen-2.5-7B, Type=Our Implementations2025.0863.363.2
R1-Searcher++Model=Qwen-2.5-7B, Type=RAG-RL2025.0860.859.2
UR2Model=LLaMA-3.1-8B, Type=Our Implementations2025.0860.763.2
Vanilla RLModel=LLaMA-3.1-8B, Type=Our Implementations2025.0860.663.2
Self-AskModel=GPT-4o-mini, Type=Advanced RAG2025.0859.357.6
Vanilla RLModel=Qwen-2.5-3B, Type=Our Implementations2025.085957.6
Search-R1Model=Qwen-2.5-7B, Type=RAG-RL2025.0858.956.8
UR2Model=Qwen-2.5-3B, Type=Our Implementations2025.0857.858.4
R1-SearcherModel=Qwen-2.5-7B, Type=RAG-RL2025.0856.553.6
CoTModel=GPT-4o-mini, Type=Vanilla Methods2025.0855.262.4
Search-o1Model=GPT-4o-mini, Type=Advanced RAG2025.0854.556
RATModel=GPT-4o-mini, Type=Advanced RAG2025.085351.2
Search-R1Model=Qwen-2.5-3B, Type=RAG-RL2025.0848.348
Standard RAGModel=GPT-4o-mini, Type=Vanilla Methods2025.0846.746.4
CoTModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.084342.4
Self-AskModel=LLaMA-3.1-8B, Type=Advanced RAG2025.0841.544.8
CoTModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0841.343.2
RATModel=LLaMA-3.1-8B, Type=Advanced RAG2025.0839.739.2
Standard RAGModel=Qwen-2.5-7B, Type=Vanilla Methods2025.0838.940
Search-o1Model=Qwen-2.5-7B, Type=Advanced RAG2025.0837.539.2
ZeroSearchModel=Qwen-2.5-7B, Type=RAG-RL2025.0835.838.4
Zero-SearchModel=Qwen-2.5-3B, Type=RAG-RL2025.0832.431.2
RATModel=Qwen-2.5-7B, Type=Advanced RAG2025.0831.630.4
Search-o1Model=Qwen-2.5-3B, Type=Advanced RAG2025.0831.432
CoTModel=Qwen-2.5-3B, Type=Vanilla Methods2025.0831.233.6
Self-AskModel=Qwen-2.5-3B, Type=Advanced RAG2025.0830.632
RATModel=Qwen-2.5-3B, Type=Advanced RAG2025.0830.628
Search-o1Model=LLaMA-3.1-8B, Type=Advanced RAG2025.083030.4
Self-AskModel=Qwen-2.5-7B, Type=Advanced RAG2025.0828.942.4
Standard RAGModel=LLaMA-3.1-8B, Type=Vanilla Methods2025.0826.528
Standard RAGModel=Qwen-2.5-3B, Type=Vanilla Methods2025.0826.127.2