MedDialBench - Fabricating + Denial: 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 a patient who fabricates symptoms and is in complete denial. 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 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 2030. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.4Non-reasoning40#138
2DeepSeek V3.2Non-reasoning38.8#425
3Gemini 3.1 Pro (Preview)36.5#102
4Claude Opus 4.636.5#114
5Qwen 3.5 PlusNon-reasoning35.3#250

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=meddialbench-fabricating-plus-denial · How It Works · Data refreshed daily, snapshot 2026-11-22.