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

#ModelScoreOverall rank
1Gemini 2.5 Pro44.48#276
2Gemini 2.5 Pro (Thinking Budget: 128)39.27
3Gemini 2.5 Flash33.68#463
4Qwen 3 235B A22B22.49#628
5CulturALL qwen-max (checkpoint unspecified)19.31
6Qwen 3 30B A3B17.62#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.