Red Flags Detection on RealICU-Scale (test)
29.2HRRICU-Evo
Evaluation Results
| Method | Links | |
|---|---|---|
| ICU-EvoBackbone=Qwen3-235B [34], System=ICU-Evo2026.05 | 29.2 | |
| RAGBackbone=Qwen3-235B [34], System=RAG2026.05 | 22.5 | |
| Full-contextBackbone=Qwen3-235B [34], System=Full-context2026.05 | 21.5 | |
| Local-windowBackbone=Qwen3-235B [34], System=Local-window2026.05 | 20.7 | |
| RAGBackbone=GPT-5.4 [22], System=RAG2026.05 | 9.6 | |
| ICU-EvoBackbone=GPT-5.4 [22], System=ICU-Evo2026.05 | 9 | |
| ICU-EvoBackbone=Gemini-3.1-pro [8], System=ICU-Evo2026.05 | 8.7 | |
| RAGBackbone=Gemini-3.1-pro [8], System=RAG2026.05 | 7.3 | |
| Local-windowBackbone=GPT-5.4 [22], System=Local-window2026.05 | 7.3 | |
| Local-windowBackbone=Gemini-3.1-pro [8], System=Local-window2026.05 | 6.6 |