Multi-Agent Clinical Evaluation on Combined Medical Benchmarks Aggregate
8.9Expert RatingMulti-Agent Medical Decision Consensus Matrix System
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Multi-Agent Medical Decision Consensus Matrix System2025.12 | 8.9 | 0.823 | |
| TeamMedAgents2025.12 | 8 | 0.674 | |
| MDAgents2025.12 | 7.8 | 0.651 | |
| Weighted VotingMulti-Agent Aggregation Method=Weighted Voting2025.12 | 7.6 | 0.589 | |
| Majority VotingMulti-Agent Aggregation Method=Majority Voting2025.12 | 7.4 | 0.542 | |
| Borda CountMulti-Agent Aggregation Method=Borda Count2025.12 | 7.3 | 0.623 | |
| Chain-of-ThoughtPrompting Strategy=Chain-of-Thought2025.12 | 7.1 | — | |
| Single-AgentEvaluation Protocol=Few-shot2025.12 | 6.8 | — | |
| Single-AgentEvaluation Protocol=Zero-shot2025.12 | 6.2 | — |