Patient Status on RealICU GOLD
45.9AccuracyICU-Evo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ICU-EvoBackbone=Gemini-3.1-pro2026.05 | 45.9 | 36.5 | |
| RAGBackbone=Gemini-3.1-pro2026.05 | 40.2 | 34.8 | |
| Local-windowBackbone=Gemini-3.1-pro2026.05 | 31.5 | 23.9 | |
| RAGBackbone=Qwen3-235B2026.05 | 31.5 | 27.1 | |
| ICU-EvoBackbone=GPT-5.42026.05 | 31.2 | 26.4 | |
| Full-contextBackbone=Gemini-3.1-pro2026.05 | 29.8 | 25.8 | |
| Full-contextBackbone=GPT-5.42026.05 | 29.4 | 23.3 | |
| RAGBackbone=GPT-5.42026.05 | 28.8 | 25.6 | |
| ICU-EvoBackbone=Qwen3-235B2026.05 | 25.3 | 19.7 | |
| Local-windowBackbone=GPT-5.42026.05 | 23.3 | 18.4 | |
| Full-contextBackbone=Qwen3-235B2026.05 | 22.5 | 18.8 | |
| Local-windowBackbone=Qwen3-235B2026.05 | 15.2 | 15.4 |