List your company

Medical Reasoning Accuracy on DDXPlus

83.37Accuracy (DDXPlus)DMoA
47.937257.136166.33575.5339Aug 11, 2025Sep 26, 2025Nov 11, 2025Dec 27, 2025Feb 11, 2026Mar 29, 2026May 15, 2026

Evaluation results

MethodLinks
DMoABackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0583.37
SafeSieveBackbone=gpt-oss-120b2026.0577.94
MDAgentsBase Model=GPT-4o2025.0877.9
SpecReasonBackbone=gpt-oss-120b2026.0576.58
G-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0576.42
ARG-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0576.03
GPTSwarmBackbone=gpt-oss-120b2026.0575.57
STEERBackbone=gpt-oss-120b2026.0575.2
TMA-AllComponBase Model=GPT-4o2025.0874.9
AFlowBackbone=gpt-oss-120b2026.0574.25
Single-Agent BestBase Model=Gemma-3-4B2025.0872.1
MoABackbone=gpt-oss-120b2026.0571.85
AutoGenBackbone=gpt-oss-120b2026.0571.83
LLM-DebateBackbone=gpt-oss-120b2026.0571.33
Random GraphBackbone=gpt-oss-120b2026.0570.44
Complete GraphBackbone=gpt-oss-120b2026.0570.35
TMA-AllComponBase Model=MedGemma-4B2025.0870.2
TreeBackbone=gpt-oss-120b2026.0569.25
MedAgentsBase Model=Gemma-3-4B2025.0869.1
StarBackbone=gpt-oss-120b2026.0568.25
ReConcileBase Model=GPT-4o2025.0868
TMA-AllComponBase Model=Gemma-3-4B2025.0867.3
MedAgentsBase Model=GPT-4o2025.0866.6
SCBackbone=gpt-oss-120b2026.0566.43
DyLANBase Model=Gemma-3-4B2025.0865.6
TMA-AllComponBase Model=Gemma-3-4B2025.0865.3
ChainBackbone=gpt-oss-120b2026.0565.28
CoTBackbone=gpt-oss-120b2026.0564.22
MedAgentsBase Model=Gemma-3-4B2025.0861
DyLanBase Model=Gemma-3-4B2025.0860
ReConcileBase Model=Gemma-3-4B2025.0858
VanillaBackbone=gpt-oss-120b2026.0556.4
DyLANBase Model=GPT-4o2025.0856
ReConcileBase Model=Gemma-3-4B2025.0854
MDAgentsBase Model=Gemma-3-4B2025.0852.6
MDAgentsBase Model=Gemma-3-4B2025.0849.3