List your company

Professional Consensus Building on MedQA

84.83MedQA AccuracyCAMEL
29.023643.51185872.4882Mar 26, 2026

Evaluation results

MethodLinks
CAMELBase Model=Qwen3-30B-A3B2026.0384.83
BEACOFBase Model=Qwen3-30B-A3B2026.0384.67
ReConcileBase Model=Qwen3-30B-A3B2026.0373.25
MADBase Model=Qwen3-30B-A3B2026.0371.83
ReConcileBase Model=Gemma3-12B2026.0355.5
BEACOFBase Model=Gemma3-12B2026.0355.5
CAMELBase Model=Gemma3-12B2026.0354.5
BEACOFBase Model=Llama3.1-8B-Instruct2026.0352.23
CAMELBase Model=Llama3.1-8B-Instruct2026.0352.17
ReConcileBase Model=Llama3.1-8B-Instruct2026.0344.75
MADBase Model=Llama3.1-8B-Instruct2026.0334.5
MADBase Model=Gemma3-12B2026.0331.17