List your company

Multi-turn Medical Diagnosis on Med-Inquire DiagnosisArena (915 cases)

59.8Mean Diagnostic GradeEvoClinician
38.06443.70749.3554.993Jan 30, 2026

Evaluation results

MethodLinks
EvoClinicianBackbone=gemini-3-pro2026.0159.89.11,275
EvoTestBackbone=gemini-3-pro2026.0157.99.41,605
EvoClinicianBackbone=gpt-5.12026.0154.29.31,310
EvoPromptBackbone=gemini-3-pro2026.0153.69.71,360
EvoTestBackbone=gpt-5.12026.0152.59.61,650
Evo-MemoryBackbone=gemini-3-pro2026.0152101,435
Mem0Backbone=gemini-3-pro2026.0151.210.11,450
EvoClinicianBackbone=MedGemma-27b2026.0151.19.51,328
RAGBackbone=gemini-3-pro2026.0150.710.31,490
MemoryBackbone=gemini-3-pro2026.0150.110.41,510
EvoTestBackbone=MedGemma-27b2026.0149.69.71,670
GEPABackbone=gemini-3-pro2026.0149.410.61,540
EvoPromptBackbone=gpt-5.12026.01499.91,390
Static PromptBackbone=gemini-3-pro2026.0148.29.81,380
EvoClinicianBackbone=gpt-4o-mini2026.01489.61,345
Evo-MemoryBackbone=gpt-5.12026.0147.110.31,465
EvoPromptBackbone=MedGemma-27b2026.0146.6101,405
EvoTestBackbone=gpt-4o-mini2026.0146.69.81,690
Mem0Backbone=gpt-5.12026.0146.310.41,480
RAGBackbone=gpt-5.12026.0145.710.61,520
MemoryBackbone=gpt-5.12026.0145.110.71,540
Evo-MemoryBackbone=MedGemma-27b2026.0144.810.51,480
GEPABackbone=gpt-5.12026.0144.610.91,575
EvoPromptBackbone=gpt-4o-mini2026.0144.110.21,420
Mem0Backbone=MedGemma-27b2026.014410.61,495
Static PromptBackbone=gpt-5.12026.0143.610.11,410
RAGBackbone=MedGemma-27b2026.0143.310.81,535
MemoryBackbone=MedGemma-27b2026.0142.810.91,560
Evo-MemoryBackbone=gpt-4o-mini2026.0142.510.61,495
GEPABackbone=MedGemma-27b2026.0142.2111,593
Mem0Backbone=gpt-4o-mini2026.0141.710.71,510
Static PromptBackbone=MedGemma-27b2026.014110.21,425
RAGBackbone=gpt-4o-mini2026.0140.910.91,550
MemoryBackbone=gpt-4o-mini2026.0140.4111,580
GEPABackbone=gpt-4o-mini2026.0139.811.21,610
Static PromptBackbone=gpt-4o-mini2026.0138.910.41,440