CulturALL (Web Search): leaderboard
Multilingual and multicultural competence on grounded everyday tasks from CulturALL (2026), with the model allowed to use web search: 2,610 scenario questions in 14 languages from 51 regions across 16 topics, written with native-speaker annotators. Accuracy in percent judged against reference answers; higher is better.
Metric: Accuracy (%) with the model's web search tool enabled 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 February 2027. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 44.48 | #276 |
| 2 | Gemini 2.5 Pro (Thinking Budget: 128) | 39.27 | |
| 3 | Gemini 2.5 Flash | 33.68 | #463 |
| 4 | Qwen 3 235B A22B | 22.49 | #628 |
| 5 | CulturALL qwen-max (checkpoint unspecified) | 19.31 | |
| 6 | Qwen 3 30B A3B | 17.62 | #1156 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=culturall-web-search · How It Works · Data refreshed daily, snapshot 2026-11-21.