Benchmark
CulturalMenuBench
What is CulturalMenuBench?
Evaluates multimodal models on culinary reasoning across 4,870 items in 10 languages and 18 regions, with tasks from dish recognition to cultural attribution…
- Released
- 2026-09-03
- Evaluates
- Factuality, General AI, Multimodal, Reasoning
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.03526
CulturalMenuBench paper and code
No reported scores are on record for this benchmark yet.