MedDialBench - Incoherent: leaderboard
MedDialBench (2026) has doctor-agent LLMs interview a simulated patient (Claude Opus 4.5 following case-specific behaviour scripts) on 85 OSCE cases and name a diagnosis, which Qwen3-Max judges correct or not. This board uses an incoherent patient (expression, extreme). Diagnostic accuracy in percent; higher is better.
Metric: Diagnostic accuracy (%) over 85 OSCE cases (each cell counts whole cases out of 85) after a free-form consultation with an incoherent patient (expression, extreme), the final diagnosis judged correct or not by Qwen3-Max; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 92.9 | #99 | |
| 2 | Claude Opus 4.6 | 82.4 | #113 | |
| 3 | GPT-5.4 | Non-reasoning | 81.2 | #135 |
| 4 | Qwen 3.5 Plus | Non-reasoning | 76.5 | #242 |
| 5 | DeepSeek V3.2 | Non-reasoning | 72.9 | #419 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=meddialbench-incoherent · How It Works · Data refreshed daily, snapshot 2026-11-21.