Acute Problems Prediction on RealICU-Scale (test)
85.2Hit@5ICU-Evo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ICU-EvoBackbone=GPT-5.4 [22], System=ICU-Evo2026.05 | 85.2 | 56.2 | |
| ICU-EvoBackbone=Gemini-3.1-pro [8], System=ICU-Evo2026.05 | 82.7 | 51.8 | |
| ICU-EvoBackbone=Qwen3-235B [34], System=ICU-Evo2026.05 | 64.9 | 37.5 | |
| RAGBackbone=GPT-5.4 [22], System=RAG2026.05 | 58.4 | 32.1 | |
| RAGBackbone=Gemini-3.1-pro [8], System=RAG2026.05 | 56.8 | 31.5 | |
| Local-windowBackbone=Gemini-3.1-pro [8], System=Local-window2026.05 | 48.7 | 26.5 | |
| Local-windowBackbone=GPT-5.4 [22], System=Local-window2026.05 | 47.5 | 26.6 | |
| Full-contextBackbone=Qwen3-235B [34], System=Full-context2026.05 | 40.1 | 23.2 | |
| RAGBackbone=Qwen3-235B [34], System=RAG2026.05 | 37.9 | 20.7 | |
| Local-windowBackbone=Qwen3-235B [34], System=Local-window2026.05 | 25.4 | 14.2 |