Knowledge-Driven Structured EHR Understanding and Reasoning on Synthea
58.7K-R1 AUCGemini 2.5
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini 2.5Model Type=General LLMs, Setting=Zero-shot2025.11 | 58.7 | — | 54.1 | — | |
| Qwen-32BModel Type=General LLMs, Setting=Zero-shot2025.11 | 58.3 | — | 51 | — | |
| GPT-3.5 TurboModel Type=General LLMs, Setting=Zero-shot2025.11 | 58.1 | — | 55.4 | 52.9 | |
| Gemini-2.0Model Type=General LLMs, Setting=Zero-shot2025.11 | 57.7 | 52 | 56.2 | 51.6 | |
| GPT-4oModel Type=General LLMs, Setting=Zero-shot2025.11 | 55.6 | 55 | 53.2 | 51 | |
| Gemini 1.5Model Type=General LLMs, Setting=Zero-shot2025.11 | 55.6 | — | — | — | |
| DeepSeek-V3Model Type=General LLMs, Setting=Zero-shot2025.11 | 52.8 | — | — | — | |
| DeepSeek-V2.5Model Type=General LLMs, Setting=Zero-shot2025.11 | — | 51 | — | — | |
| Qwen-72BModel Type=General LLMs, Setting=Zero-shot2025.11 | — | — | — | 52.2 |