List your company

Medical Diagnosis on MedEinst Baseline 1.0

69.49Baseline AccuracyECR-Agent (Qwen3-32B)
3.990820.99543855.0046Jan 10, 2026

Evaluation results

MethodLinks
ECR-Agent (Qwen3-32B)Size=32B2026.0169.49
GPT-5Size=-2026.0154.3
Gemini-2.5-proSize=-2026.0153.58
Kimi-k2Size=-2026.0147.82
Baichuan-M2-32BSize=32B2026.0145.03
Qwen/Qwen3-14BSize=14B2026.0144.12
DeepSeek-R1Size=-2026.0142.2
Claude-Sonnet-4.5Size=-2026.0142.09
Qwen/QwQ-32BSize=32B2026.0141.05
MedGemma-27B-text-itSize=27B2026.0140.92
Qwen/Qwen3-235B-A22BSize=235B2026.0140.51
Qwen/Qwen3-32BSize=32B2026.0140.25
ZhipuAI/GLM-4.6Size=-2026.0139.65
DyLAN (Qwen3-32B)Size=32B2026.0132.11
MDAgent (Qwen3-32B)Size=32B2026.0129.7
Lingshu-32BSize=32B2026.0127.68
Lingshu-7BSize=7B2026.0114.93
Llama3-Med42-8BSize=8B2026.016.51