List your company

Medical Reasoning on Professional Medicine

74.6AccuracyMajority Vote
50.1656.50562.8569.195Mar 21, 2026

Evaluation results

MethodLinks
Majority VoteModel=Llama3.1-8B2026.0374.6
Vote PromptBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0373.2
Society Of MindBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0373
MAD-M^2Backbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0373
MAD-M2Model=Falcon3-7B2026.0372.8
DARModel=Falcon3-7B2026.0372.8
Vote PromptModel=Falcon3-7B2026.0372.7
DARBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0372.7
Uncertain PromptModel=Falcon3-7B2026.0372.3
Uncertain PromptBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0372.3
DARModel=Llama3.1-8B2026.0372.2
Majority VoteBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0372.1
Society Of MindModel=Falcon3-7B2026.0371.9
DARBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0371.2
Uncertain PromptModel=Llama3.1-8B2026.0370.6
Single-agentModel=Falcon3-7B2026.0370.3
Single-agentBackbone Model=Falcon3-7B2026.0370.3
Majority VoteBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0370
Majority VoteModel=Falcon3-7B2026.0368.7
Vote PromptModel=Llama3.1-8B2026.0367.9
Uncertain PromptBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0367.9
MAD-M^2Backbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0366.7
Society Of MindBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0366.5
Single-agentModel=Llama3.1-8B2026.0366.3
Single-agentBackbone Model=Llama3.1-8B2026.0366.3
MAD-M2Model=Llama3.1-8B2026.0366.1
Vote PromptBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0365.8
DARModel=Qwen2.5-3B2026.0365.6
Uncertain PromptBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0365.6
DARBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0365.1
MAD-M2Model=Qwen2.5-3B2026.0364.8
Vote PromptModel=Qwen2.5-3B2026.0364.8
MAD-M^2Backbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0364.7
Society Of MindModel=Qwen2.5-3B2026.0364.5
Uncertain PromptModel=Qwen2.5-3B2026.0364.1
Society Of MindBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0363.8
Majority VoteModel=Qwen2.5-3B2026.0363.7
Majority VoteBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0363.6
Vote PromptBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0362.7
Society Of MindModel=Llama3.1-8B2026.0361.8
Single-agentBackbone Model=Qwen2.5-3B2026.0359.8
Single-agentModel=Qwen2.5-3B2026.0358.8
DARBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0358.7
Majority VoteModel=Qwen2.5-1.5B2026.0358.6
Majority VoteBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0358.6
Vote PromptBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0358.6
Vote PromptModel=Qwen2.5-1.5B2026.0357.7
Society Of MindBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0357.7
Uncertain PromptBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0357.7
Society Of MindModel=Qwen2.5-1.5B2026.0357.6
Uncertain PromptModel=Qwen2.5-1.5B2026.0357.6
MAD-M2Model=Qwen2.5-1.5B2026.0357.5
MAD-M^2Backbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0357.4
Single-agentModel=Qwen2.5-1.5B2026.0355.6
Single-agentBackbone Model=Qwen2.5-1.5B2026.0355.6
DARModel=Qwen2.5-1.5B2026.0351.1