Intraoperative Safety Monitoring on Surgical Tasks Dataset
74.5EWSSURGENT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SURGENTCategory=Multi-agent, LLM=DeepSeek2026.05 | 74.5 | 33.2 | |
| ColaCareCategory=Multi-agent, LLM=DeepSeek2026.05 | 68.4 | 37.8 | |
| MDAgentsCategory=Multi-agent, LLM=DeepSeek2026.05 | 67.3 | 37 | |
| MedAgentsCategory=Multi-agent, LLM=DeepSeek2026.05 | 65.2 | 40.1 | |
| ReConcileCategory=Multi-agent, LLM=DeepSeek2026.05 | 64.1 | 38.2 | |
| CoT-SCCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 63 | 43.5 | |
| MedPromptCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 62.3 | 42.8 | |
| CoTCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 61.1 | 45.4 | |
| SCCategory=Advanced Single-agent, LLM=DeepSeek2026.05 | 60.2 | 46.3 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=DeepSeek2026.05 | 58.2 | 50.7 | |
| Few-shotCategory=Vanilla Single-agent, LLM=DeepSeek2026.05 | 56.3 | 45.1 | |
| Few-shotCategory=Vanilla Single-agent, LLM=Claude2026.05 | 55.2 | 46.5 | |
| Few-shotCategory=Vanilla Single-agent, LLM=GPT-4o2026.05 | 51.5 | 49.3 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=Claude2026.05 | 50.3 | 52.8 | |
| Zero-shotCategory=Vanilla Single-agent, LLM=GPT-4o2026.05 | 45.1 | 56.3 |