List your company

Final Diagnosis Prediction on MedCaseReasoning

66AccuracyCounterfactual Multi-agent Diagnostic Framework
5.6821.343752.66Mar 29, 2026

Evaluation results

MethodLinks
Counterfactual Multi-agent Diagnostic FrameworkModel=GPT-4o mini, Setting=Agents2026.0366
MDAgentsModel=GPT-4o mini, Setting=Agents2026.0360.7
MACModel=GPT-4o mini, Setting=Agents2026.0359.3
Counterfactual Multi-agent Diagnostic FrameworkModel=Deepseek R1, Setting=Agents2026.0354
FSModel=GPT-4o mini, Setting=Prompting2026.0352
FS CoTModel=GPT-4o mini, Setting=Prompting2026.0352
FS CoTModel=Deepseek R1, Setting=Prompting2026.0350.7
ZSModel=GPT-4o mini, Setting=Prompting2026.0350.7
MedAgentsModel=Deepseek R1, Setting=Agents2026.0349.3
ZS CoTModel=GPT-4o mini, Setting=Prompting2026.0347.3
MedAgentsModel=GPT-4o mini, Setting=Agents2026.0347.3
ZS CoTModel=Deepseek R1, Setting=Prompting2026.0344.7
FSModel=Deepseek R1, Setting=Prompting2026.0344.7
ZSModel=Deepseek R1, Setting=Prompting2026.0342
MACModel=Deepseek R1, Setting=Agents2026.0340.7
MDAgentsModel=Deepseek R1, Setting=Agents2026.0338.7
Counterfactual Multi-agent Diagnostic FrameworkModel=Qwen, Setting=Agents2026.0326.3
ZSModel=Qwen, Setting=Prompting2026.0325.3
ZS CoTModel=Qwen, Setting=Prompting2026.0325.3
MedAgentsModel=Qwen, Setting=Agents2026.0324.7
FSModel=Qwen, Setting=Prompting2026.0323.3
Counterfactual Multi-agent Diagnostic FrameworkModel=m1-7B-23k, Setting=Agents2026.0323.3
FS CoTModel=Qwen, Setting=Prompting2026.0323
Counterfactual Multi-agent Diagnostic FrameworkModel=Llama, Setting=Agents2026.0322.7
MDAgentsModel=Qwen, Setting=Agents2026.0322
MACModel=Qwen, Setting=Agents2026.0321.3
Counterfactual Multi-agent Diagnostic FrameworkModel=medgemma, Setting=Agents2026.0321
Counterfactual Multi-agent Diagnostic FrameworkModel=MedReason, Setting=Agents2026.0320.3
ZSModel=m1-7B-23k, Setting=Prompting2026.0320
MDAgentsModel=m1-7B-23k, Setting=Agents2026.0319
MDAgentsModel=Llama, Setting=Agents2026.0318.7
ZS CoTModel=m1-7B-23k, Setting=Prompting2026.0318.7
MDAgentsModel=MedReason, Setting=Agents2026.0318.7
MACModel=medgemma, Setting=Agents2026.0318.3
ZS CoTModel=Llama, Setting=Prompting2026.0318
MedAgentsModel=MedReason, Setting=Agents2026.0318
ZSModel=medgemma, Setting=Prompting2026.0318
FSModel=Llama, Setting=Prompting2026.0317.7
ZS CoTModel=medgemma, Setting=Prompting2026.0317.7
ZSModel=Llama, Setting=Prompting2026.0317.3
MACModel=Llama, Setting=Agents2026.0317.3
ZSModel=MedReason, Setting=Prompting2026.0317.3
MedAgentsModel=Llama, Setting=Agents2026.0316.3
MACModel=m1-7B-23k, Setting=Agents2026.0316.3
MACModel=MedReason, Setting=Agents2026.0316.3
MedAgentsModel=m1-7B-23k, Setting=Agents2026.0316
FSModel=medgemma, Setting=Prompting2026.0315.3
FS CoTModel=Llama, Setting=Prompting2026.0314.3
FSModel=m1-7B-23k, Setting=Prompting2026.0313.7
ZS CoTModel=MedReason, Setting=Prompting2026.0313
FS CoTModel=medgemma, Setting=Prompting2026.0312.7
MDAgentsModel=medgemma, Setting=Agents2026.0312.7
FS CoTModel=MedReason, Setting=Prompting2026.0312
MedAgentsModel=medgemma, Setting=Agents2026.0311.3
FS CoTModel=m1-7B-23k, Setting=Prompting2026.0311
FSModel=MedReason, Setting=Prompting2026.038