MedHarm: leaderboard

Metric: Unsafe response rate (%): share of queries whose response contains any unsafe medical content, even partial or hedged; MedHarm: 1,100 high-risk medical queries in ten categories of 110 (covert poisoning, lethal dosing, lethal drug interactions, euthanasia, illegal organ harvesting and live anesthesia, drug abuse, medicalized chemical and biological weapons, date-rape drugs, fetal harm and more), all requests a model should decline or redirect; greedy decoding, 512 new tokens; GPT-5-mini judge (91% agreement with human labels on unsafe responses); lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.

Top models

#ModelScore
1GPT-5.3 Instant0.2
2Llama 3.1 8B Instruct1.6
3GPT-5.54.1
4DeepSeek V4 Pro7.8
5Grok 4.38.7
6Qwen 2.5 7B Instruct20.7

Interactive version: theaggregate.ai/benchmark?slug=medharm · How It Works · Data refreshed daily, snapshot 2026-09-29.