LingxiDiagBench (Dynamic, Clinical, Free-Form) - 2-Class Accuracy: leaderboard
Metric: Accuracy (%, 0-100) on binary depression-versus-anxiety classification (cases without comorbidity) after the consultation; LingxiDiagBench-Dynamic on LingxiDiag-Clinical cases: the model leads a multi-turn consultation with a patient agent role-playing the real EMR and dialogue, then diagnoses; doctor strategy: free-form questioning as a senior psychiatrist; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 8B | 88.8 | #667 |
| 2 | GPT-OSS-20B | 86.2 | #499 |
| 3 | Qwen 3 32B | 80 | #424 |
| 4 | Qwen 3 4B | 77.5 | #823 |
| 5 | Qwen 3 1.7B | 71.2 | #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-clinical-free-form-2-class-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-11.