List your company

Medical Diagnosis on MedEinst Robust 1.0

24.21Robust AccuracyECR-Agent (Qwen3-32B)
0.26926.484612.718.9154Jan 10, 2026

Evaluation results

MethodLinks
ECR-Agent (Qwen3-32B)Size=32B2026.0124.2133.75
GPT-5Size=-2026.0115.7851.87
Kimi-k2Size=-2026.0112.4647.12
Claude-Sonnet-4.5Size=-2026.0112.3642.98
Qwen/Qwen3-32BSize=32B2026.0111.8643.46
MedGemma-27B-text-itSize=27B2026.0111.6853.88
Qwen/Qwen3-235B-A22BSize=235B2026.0111.443.32
DeepSeek-R1Size=-2026.0111.3246.12
Qwen/Qwen3-14BSize=14B2026.0111.2854.19
ZhipuAI/GLM-4.6Size=-2026.0111.2547.63
Qwen/QwQ-32BSize=32B2026.0111.1444.88
Gemini-2.5-proSize=-2026.0110.9760.9
MDAgent (Qwen3-32B)Size=32B2026.0110.3440.34
DyLAN (Qwen3-32B)Size=32B2026.018.1141.69
Baichuan-M2-32BSize=32B2026.017.1866.1
Lingshu-32BSize=32B2026.016.1754.2
Lingshu-7BSize=7B2026.013.236.74
Llama3-Med42-8BSize=8B2026.011.1944