Medical Question Answering on MedicalQA
86AccuracySymphony-Coord
Evaluation Results
| Method | Links | |
|---|---|---|
| Symphony-CoordBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 86 | |
| MetaGPTBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 84 | |
| GPTSwarmBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 83 | |
| MetaGPTBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 82 | |
| Symphony-CoordBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 82 | |
| Symphony-CoordBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 81 | |
| AFLOWBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 80 | |
| MetaGPTBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 80 | |
| AFLOWBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 80 | |
| AFLOWBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 77 | |
| GPTSwarmBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 76 | |
| GPTSwarmBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 73 | |
| MorphagentBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 64 | |
| DirectBackbone=DeepSeek-V3-0324, Category=Single Agent2026.02 | 54 | |
| SynapseBackbone=DeepSeek-V3, Category=Single Agent2026.02 | 53 | |
| ReactBackbone=DeepSeek-V3-0324, Category=Single Agent2026.02 | 53 | |
| Self-ConsistencyBackbone=DeepSeek-V3-0324, Category=Single Agent2026.02 | 53 | |
| Self-RefinementBackbone=DeepSeek-V3-0324, Category=Single Agent2026.02 | 53 | |
| SynapseBackbone=DeepSeek-V3-0324, Category=Single Agent2026.02 | 51 | |
| DirectBackbone=GPT-5-nano, Category=Single Agent2026.02 | 51 | |
| Self-RefinementBackbone=DeepSeek-V3, Category=Single Agent2026.02 | 50 | |
| Cold StartBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 50 | |
| ReactBackbone=DeepSeek-V3, Category=Single Agent2026.02 | 49 | |
| Self-ConsistencyBackbone=DeepSeek-V3, Category=Single Agent2026.02 | 48 | |
| Cold StartBackbone=DeepSeek-V3-0324, Category=Multi-Agent2026.02 | 48 | |
| MorphagentBackbone=DeepSeek-V3, Category=Multi-Agent2026.02 | 47 | |
| SynapseBackbone=GPT-5-nano, Category=Single Agent2026.02 | 47 | |
| Self-RefinementBackbone=GPT-5-nano, Category=Single Agent2026.02 | 47 | |
| DirectBackbone=DeepSeek-V3, Category=Single Agent2026.02 | 45 | |
| ReactBackbone=GPT-5-nano, Category=Single Agent2026.02 | 44 | |
| Self-ConsistencyBackbone=GPT-5-nano, Category=Single Agent2026.02 | 43 | |
| MorphagentBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 42 | |
| Cold StartBackbone=GPT-5-nano, Category=Multi-Agent2026.02 | 17 |