MedDialBench - Fabricating + Denial: leaderboard
Metric: Diagnostic accuracy (%) over 85 OSCE cases (each cell counts whole cases out of 85) after a free-form consultation with a patient who fabricates and is in complete denial (combination C3), the final diagnosis judged correct or not by Qwen3-Max; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Non-reasoning) | 40 |
| 2 | DeepSeek V3.2 (Non-reasoning) | 38.8 |
| 3 | Gemini 3.1 Pro (Preview) | 36.5 |
| 4 | Claude Opus 4.6 | 36.5 |
| 5 | Qwen 3.5 Plus (Non-reasoning) | 35.3 |
Interactive version: theaggregate.ai/benchmark?slug=meddialbench-fabricating-plus-denial · How It Works · Data refreshed daily, snapshot 2026-10-07.