CulturalRiddles: leaderboard
Multilingual cultural riddle benchmark from Cohere Labs Community (arXiv:2610.29968) featuring original riddles written by native speakers across 57 human-evaluated communities and 51 languages. Scored by accuracy (%) combining exact-match rules, anonymous native-speaker review, and a two-model LLM jury.
Metric: Accuracy with human & LLM-jury review (%, 57 communities). Source: huggingface.co. Saturation forecast: Around February 2027. 25 models tracked. Updated 20 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 79.4 | #101 | |
| 2 | GPT-5.5 | Non-reasoning | 76.3 | #54 |
| 3 | Claude Opus 4.7 | High | 66 | #85 |
| 4 | DeepSeek V4 Pro | High | 63.8 | #198 |
| 5 | Gemini 2.5 Flash | 50.1 | #469 | |
| 6 | Gemma 4 31B (IT) | 39.6 | #354 | |
| 7 | DeepSeek V4 Flash | 39.2 | #267 | |
| 8 | Mistral Large 3 | 38.5 | #835 | |
| 9 | Gemini 2.5 Flash Lite | 33.6 | #974 | |
| 10 | Qwen-SEA-LION-v4.5-27B-IT | 33.5 | #603 | |
| 11 | Qwen 3.5 27B | 28 | #378 | |
| 12 | Apertus-v1.5-70B | 19.6 | #1783 | |
| 13 | Apertus-70B-Instruct-2509 | 15.2 | #2627 | |
| 14 | EuroLLM-22B-Instruct-2512 | 15 | #2012 | |
| 15 | Nova Lite | 14.7 | #2322 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=culturalriddles · How It Works · Data refreshed daily, snapshot 2026-11-20.