List your company

Medical Question Answering on DDXPlus

86.5AccuracyMulti-Agent Medical Decision Consensus Matrix System
26.59642.14857.773.252Dec 16, 2025Dec 29, 2025Jan 12, 2026Jan 26, 2026Feb 9, 2026Feb 23, 2026Mar 9, 2026

Evaluation results

MethodLinks
Multi-Agent Medical Decision Consensus Matrix System2025.1286.5
MAPLESize=8B, Inference Protocol=BoM2026.0383
ST-EVOBackbone=gpt-oss-120b2026.0282.5
TeamMedAgents2025.1282.4
MDAgents2025.1281.2
Weighted VotingMulti-Agent Aggregation Method=Weighted Voting2025.1280.3
R1-Distill-LlamaSize=8B, Inference Protocol=MV2026.0380
Majority VotingMulti-Agent Aggregation Method=Majority Voting2025.1279.5
Med-PRMSize=8B, Inference Protocol=BoM2026.0379
Borda CountMulti-Agent Aggregation Method=Borda Count2025.1278.9
Chain-of-ThoughtPrompting Strategy=Chain-of-Thought2025.1278.2
Med-PRMSize=8B, Inference Protocol=SC + RM2026.0378
SafeSieveBackbone=gpt-oss-120b2026.0277.94
Single-AgentEvaluation Protocol=Few-shot2025.1276.8
SpecReasonBackbone=gpt-oss-120b2026.0276.58
G-DesignerBackbone=gpt-oss-120b2026.0276.42
ARG-DesignerBackbone=gpt-oss-120b2026.0276.03
GPTSwarmBackbone=gpt-oss-120b2026.0275.57
STEERBackbone=gpt-oss-120b2026.0275.2
AFlowBackbone=gpt-oss-120b2026.0274.25
Single-AgentEvaluation Protocol=Zero-shot2025.1274.1
Llama3.1Size=8B, Inference Protocol=MV2026.0374
LangGraphBackbone=gpt-oss-120b2026.0272.5
UltraMedicalSize=8B, Inference Protocol=MV2026.0372
AutoGenBackbone=gpt-oss-120b2026.0271.83
LLM-DebateBackbone=gpt-oss-120b2026.0271.33
Random GraphBackbone=gpt-oss-120b2026.0270.44
Complete GraphBackbone=gpt-oss-120b2026.0270.35
TreeBackbone=gpt-oss-120b2026.0269.25
Gemma 2Size=9B, Inference Protocol=MV2026.0369
StarBackbone=gpt-oss-120b2026.0268.25
SCBackbone=gpt-oss-120b2026.0266.43
Llama3.1Size=8B, Inference Protocol=pass@12026.0366.41
ChainBackbone=gpt-oss-120b2026.0265.28
CoTBackbone=gpt-oss-120b2026.0264.22
Gemma 2Size=9B, Inference Protocol=pass@12026.0363.8
UltraMedicalSize=8B, Inference Protocol=pass@12026.0363.59
R1-Distill-QwenSize=7B, Inference Protocol=MV2026.0362
HuatuoGPT-o1Size=8B, Inference Protocol=pass@12026.0358.33
HuatuoGPT-o1Size=8B, Inference Protocol=MV2026.0358.33
VanillaBackbone=gpt-oss-120b2026.0256.4
R1-Distill-LlamaSize=8B, Inference Protocol=pass@12026.0349.22
R1-Distill-QwenSize=7B, Inference Protocol=pass@12026.0328.9