Patient-Context Ambiguity: leaderboard
Metric: Accuracy (%). Source: arxiv.org. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 91.8 |
| 2 | Gemini 3.1 Pro (Preview) | 90.3 |
| 3 | GPT-5.5 | 89.3 |
| 4 | Llama 3.3 70B | 86.9 |
| 5 | Mistral Large | 86.4 |
Interactive version: theaggregate.ai/benchmark?slug=patient-context-ambiguity · How It Works · Data refreshed daily, snapshot 2026-09-05.