CulturALL: leaderboard
Metric: Accuracy (%) without web search on all 2,610 CulturALL items (grounded everyday tasks in 14 languages and 51 regions written with expert annotators; items that every one of the paper's 15 model settings solved were removed), zero-shot, answers judged correct or incorrect by gpt-4o-2024-11-20 against the reference; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 37.89 |
| 2 | GPT-5 (High) | 37.59 |
| 3 | GPT-5 (Low) | 37.24 |
| 4 | GPT-5 | 37.2 |
| 5 | Claude Opus 4 (20250514) (Thinking) | 36.7 |
| 6 | Claude Opus 4 (20250514) | 36.48 |
| 7 | Claude Sonnet 4 (20250514) (Thinking) | 32.76 |
| 8 | Qwen 3 235B A22B | 23.68 |
Interactive version: theaggregate.ai/benchmark?slug=culturall · How It Works · Data refreshed daily, snapshot 2026-10-07.