LLMEval-Med - Medical Language Understanding: leaderboard

Metric: Usability rate: share of responses a GPT-4o judge scores 4 or 5 of 5 against an expert checklist (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.

Top models

#ModelScore
1DeepSeek R169.64
2O1 Preview63.85
3O1 Mini60.09
4GPT-4o56.34
5DeepSeek V353.68

Interactive version: theaggregate.ai/benchmark?slug=llmeval-med-medical-language-understanding · How It Works · Data refreshed daily, snapshot 2026-09-25.