LingxiDiagBench (Dynamic, Symptom-Tree) - Consultation Quality: leaderboard
Metric: Consultation quality (1-6): mean of five Likert dimensions (clinical accuracy and competence, ethical and professional conduct, assessment and response, therapeutic relationship, communication quality), each the mean of three LLM judges (Gemma-3-27B, GPT-OSS-20B, Qwen3-30B-A3B); LingxiDiagBench-Dynamic on LingxiDiag-16K cases: the model leads a multi-turn consultation with a Qwen3-32B patient agent built from the case EMR, then diagnoses; doctor strategy: the MDD-5K symptom decision-tree strategy; higher is better. Source: arxiv.org. Saturation forecast: Around 2032. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 3.6 | #93 |
| 2 | Kimi K2 (Thinking) | 3.59 | #236 (Kimi K2) |
| 3 | GPT-5 Mini | 3.56 | #176 |
| 4 | DeepSeek V3.2 | 3.54 | #198 |
| 5 | Qwen 3 32B | 3.5 | #424 |
| 6 | GPT-OSS-20B | 3.36 | #499 |
| 7 | Claude Haiku 4.5 | 3.24 | #271 |
| 8 | Qwen 3 4B | 3.17 | #823 |
| 9 | Qwen 3 8B | 3.15 | #667 |
| 10 | Grok 4.1 Fast | 2.98 | #208 |
| 11 | Qwen 3 1.7B | 2.93 | #1186 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=lingxidiagbench-dynamic-symptom-tree-consultation-quality · How It Works · Data refreshed daily, snapshot 2026-10-11.