CCBench-Health: leaderboard
CCBench-Health (2026) tests whether LLMs adapt health advice to cultural norms that 60 personas from six cultures signal only implicitly in earlier conversation, scoring answers against persona-specific checklists of norms to follow or avoid. Cultural Competence Score, the harmonic mean of follow and avoid rates, in percent with the conversation history given; higher is better.
Metric: Cultural Competence Score (%; harmonic mean of the follow rate and the avoid rate, the shares of checklist recommendations satisfied for norms a persona follows or avoids; 60 personas with graded norm-adherence states across six cultures (Afghan, Burmese, Chinese, Maori, Nepali, Vietnamese), 52 real health questions each (3,120 interactions); GPT-5.2 checklist evaluator; temperature 0.7; the persona conversation history is given before the question and the norms must be inferred from it)). Source: arxiv.org. Saturation forecast: Around September 2028. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 11.5 | #176 |
| 2 | Qwen 3.5 397B A17B | 10.9 | #246 |
| 3 | Gemini 2.5 Pro | 8.8 | #266 |
| 4 | Llama 3.2 90B | 4.9 | #1733 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ccbench-health · How It Works · Data refreshed daily, snapshot 2026-11-13.