Surgical Analysis on Surgical Tasks Dataset
93.1DCSURGENT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SURGENTCategory=Multi-agent, LLM=DeepSeek2026.05 | 93.1 | 83.2 | |
| ColaCareCategory=Multi-agent, LLM=DeepSeek2026.05 | 89.7 | 76.4 | |
| MedAgentsCategory=Multi-agent, LLM=DeepSeek2026.05 | 88.2 | 75.3 | |
| ReConcileCategory=Multi-agent, LLM=DeepSeek2026.05 | 87.5 | 78.5 | |
| MDAgentsCategory=Multi-agent, LLM=DeepSeek2026.05 | 86.4 | 77.6 | |
| MedPromptCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 83.5 | 72.4 | |
| Few-shotCategory=Vanilla Single-agent, LLM=Claude2026.05 | 83 | 64.3 | |
| CoTCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 82.7 | 71.5 | |
| SCCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 81.3 | 70.2 | |
| Few-shotCategory=Vanilla Single-agent, LLM=GPT-4o2026.05 | 80.2 | 60.6 | |
| Few-shotCategory=Vanilla Single-agent, LLM=DeepSeek2026.05 | 79.8 | 65.4 | |
| CoT-SCCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 78.9 | 73.1 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=DeepSeek2026.05 | 75.6 | 68.4 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=Claude2026.05 | 72.1 | 58.8 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=GPT-4o2026.05 | 68.4 | 55.7 |