List your company

Medical Sycophancy Evaluation on Medical Sycophancy Benchmark 1.0 (test)

74.8Exp. Corr. ScoreMedDR
37.04846.84956.6566.451Sep 26, 2025

Evaluation results

MethodLinks
MedDRModel Type=Medical2025.0974.875.574.775.576.174.974.376.175.1
DentoBotModel Type=Medical2025.0974.668.186.971.375.769.976.786.974.8
Gemma3-12BModel Type=Open-source2025.0972.2697370.656.370.175.875.869.6
Claude-3-OpusModel Type=Commercial2025.0966.947.529.238.844.134.45866.945.6
LLaVA-7BModel Type=Open-source2025.0965.566.270.36867.164.171.971.967.6
Gemma3-4BModel Type=Open-source2025.0964.2636955.16368.857.86963
MedGemma-4BModel Type=Medical2025.0963.168.768.368.572.362.870.572.367.8
LLaVA-13BModel Type=Open-source2025.0962.554.963.857.660.360.66263.860.3
LLaVA-MedModel Type=Medical2025.0962.462.464.666.665.660.668.668.664.4
Gemma3-27BModel Type=Open-source2025.0961.456.474.447.332.964.252.874.455.6
Qwen2.5-VL-32BModel Type=Open-source2025.096045.62745.524.676.235.976.245
GPT-4oModel Type=Commercial2025.0959.738.229.227.432.536.431.359.736.4
Doubao-VisionModel Type=Commercial2025.0949.550.144.846.839.968.141.668.148.7
Qwen2.5-VL-3BModel Type=Open-source2025.0943.637.239.637.235.235.539.343.638.2
Llama3.2-Vision-11BModel Type=Open-source2025.0943.342.534.637.443.253.839.453.842
Qwen2.5-VL-7BModel Type=Open-source2025.0938.543.452.346.834.744.246.752.343.8