CCBench-Health (Culture-CoT): leaderboard

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; history plus a Culture-CoT instruction to reason step by step about cultural cues first)). Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro17.2
2GPT-5.217.2
3Qwen 3.5 397B A17B8.7
4Llama 3.2 90B6.9

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