List your company

Question Answering on MMLU Pro.Med.

95.59AccuracyMA-PoP
64.23472.374580.51588.6555May 7, 2026

Evaluation results

MethodLinks
MA-PoPAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, Multi-Agent Strategy=Multi-Agent2026.0595.59
Free MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=3, Multi-Agent Strategy=Multi-Agent2026.0594.49
Free MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=5, Multi-Agent Strategy=Multi-Agent2026.0594.49
Decentr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=2, Multi-Agent Strategy=Multi-Agent2026.0593.75
Decentr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=5, Multi-Agent Strategy=Multi-Agent2026.0593.75
Sparse MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=2, Multi-Agent Strategy=Multi-Agent2026.0593.75
Free MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=2, Multi-Agent Strategy=Multi-Agent2026.0593.75
Self-ConsistencyAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, Multi-Agent Strategy=Multi-Agent2026.0593.75
Sparse MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=3, Multi-Agent Strategy=Multi-Agent2026.0593.64
Decentr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=3, Multi-Agent Strategy=Multi-Agent2026.0593.38
Sparse MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=5, Multi-Agent Strategy=Multi-Agent2026.0593.38
Majority VotingAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, Multi-Agent Strategy=Multi-Agent2026.0593.38
LLPAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, Multi-Agent Strategy=Multi-Agent2026.0593.38
ISPAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, Multi-Agent Strategy=Multi-Agent2026.0592.28
Falcon-34BMulti-Agent Strategy=Single-Agent2026.0591.91
Centr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=2, Multi-Agent Strategy=Multi-Agent2026.0590.44
Centr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=3, Multi-Agent Strategy=Multi-Agent2026.0590.07
Centr. MADAgent Composition (Heterogeneous)=Qwen-32B, Falcon-34B, Gemma-27B, T (Number of agents/steps)=5, Multi-Agent Strategy=Multi-Agent2026.0590.07
Qwen-32BMulti-Agent Strategy=Single-Agent2026.0588.97
MA-PoPAggregation Method=MA-PoP, Number of Agents (M)=5, Agent Diversity=Heterogeneous2026.0587.87
Free MADNumber of Agents (M)=5, Number of Debate Rounds (T)=5, Agent Diversity=Heterogeneous2026.0587.5
Free MADNumber of Agents (M)=5, Number of Debate Rounds (T)=2, Agent Diversity=Heterogeneous2026.0587.13
Free MADNumber of Agents (M)=5, Number of Debate Rounds (T)=3, Agent Diversity=Heterogeneous2026.0587.13
Decentr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=5, Agent Diversity=Heterogeneous2026.0586.76
ISPAggregation Method=ISP, Number of Agents (M)=5, Agent Diversity=Heterogeneous2026.0586.4
Decentr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=2, Agent Diversity=Heterogeneous2026.0586.03
Decentr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=3, Agent Diversity=Heterogeneous2026.0586.03
Sparse MADNumber of Agents (M)=5, Number of Debate Rounds (T)=2, Agent Diversity=Heterogeneous2026.0586.03
Self-ConsistencyAggregation Method=Self-Consistency, Number of Agents (M)=5, Agent Diversity=Heterogeneous2026.0586.03
LLPAggregation Method=LLP, Number of Agents (M)=5, Agent Diversity=Heterogeneous2026.0585.67
Sparse MADNumber of Agents (M)=5, Number of Debate Rounds (T)=3, Agent Diversity=Heterogeneous2026.0585.29
Sparse MADNumber of Agents (M)=5, Number of Debate Rounds (T)=5, Agent Diversity=Heterogeneous2026.0585.29
Gemma-27BMulti-Agent Strategy=Single-Agent2026.0584.93
Majority VotingAggregation Method=Majority Voting, Number of Agents (M)=5, Agent Diversity=Heterogeneous2026.0584.93
Centr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=5, Agent Diversity=Heterogeneous2026.0584.19
Centr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=2, Agent Diversity=Heterogeneous2026.0583.72
Centr. MADNumber of Agents (M)=5, Number of Debate Rounds (T)=3, Agent Diversity=Heterogeneous2026.0583.33
Gemma-9BNumber of Agents (M)=1, Number of Debate Rounds (T)=12026.0580.15
Falcon-7BNumber of Agents (M)=1, Number of Debate Rounds (T)=12026.0579.04
Qwen-7BNumber of Agents (M)=1, Number of Debate Rounds (T)=12026.0578.68
Llama-8BNumber of Agents (M)=1, Number of Debate Rounds (T)=12026.0574.41
Mistral-7BNumber of Agents (M)=1, Number of Debate Rounds (T)=12026.0565.44