List your company

Medical Reasoning on Medicine MedQA M-Med

75.2MedQA ScoreSearch-o1
37.96847.63457.366.966Aug 8, 2025

Evaluation results

MethodLinks
Search-o1Backbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0875.266.670.9
RATBackbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0874.470.672.5
Self-AskBackbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0872.46870.2
CoTBackbone=GPT-4o-mini2025.0871.46769.2
Standard RAGBackbone=GPT-4o-mini2025.0870.664.267.4
UR2 (GPT Summary)Backbone=Qwen-2.5-7B2025.0869.662.866.2
UR2 (GPT summary)Backbone=LLaMA-3.1-8B2025.0868.658.463.5
UR2Model=LLaMA-3.1-8B2025.0868.658.463.5
UR2 (qw Summary)Backbone=Qwen-2.5-7B2025.0867.260.864
Vanilla RLBackbone=LLaMA-3.1-8B2025.0866.857.462.1
Vanilla RLModel=LLaMA-3.1-8B2025.0866.857.462.1
UR2 (qw summary)Backbone=LLaMA-3.1-8B2025.0865.856.261
Vanilla RLBackbone=Qwen-2.5-7B2025.0864.257.460.8
RATModel=LLaMA-3.1-8B2025.0863.85659.9
Open-Reasoner-ZeroBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0861.658.860.2
RATModel=Qwen-2.5-7B2025.086053.256.6
UR2 (GPT summary)Backbone=Qwen-2.5-3B2025.0859.856.858.3
UR2Model=Qwen-2.5-3B2025.0859.856.858.3
CoTBackbone=LLaMA-3.1-8B2025.0859.652.656.1
CoTModel=LLaMA-3.1-8B2025.0859.652.656.1
General ReasonerBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0858.454.456.4
Search-o1Model=Qwen-2.5-7B2025.0858.252.855.6
CoTBackbone=Qwen-2.5-7B2025.0857.25254.6
SimpleRL-ZooBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0857.25154.1
Standard RAGBackbone=LLaMA-3.1-8B2025.0856.453.254.8
Standard RAGModel=LLaMA-3.1-8B2025.0856.453.254.8
Search-o1Model=LLaMA-3.1-8B2025.08564656.6
UR2 (qw summary)Backbone=Qwen-2.5-3B2025.0855.25454.6
Standard RAGBackbone=Qwen-2.5-7B2025.0854.253.253.7
Self-AskModel=LLaMA-3.1-8B2025.085342.847.9
Vanilla RLBackbone=Qwen-2.5-3B2025.0851.847.649.7
Self-AskModel=Qwen-2.5-7B2025.0851.847.849.8
Vanilla RLModel=Qwen-2.5-3B2025.0851.847.649.7
RATModel=Qwen-2.5-3B2025.0847.442.645
Standard RAGBackbone=Qwen-2.5-3B2025.0845.64042.8
Standard RAGModel=Qwen-2.5-3B2025.0845.64042.8
Search-o1Model=Qwen-2.5-3B2025.0844.637.441
Self-AskModel=Qwen-2.5-3B2025.0839.63637.8
CoTBackbone=Qwen-2.5-3B2025.0839.436.838.1
CoTModel=Qwen-2.5-3B2025.0839.436.838.1