CulturalMenuBench - Sub-Region Classification: leaderboard
Metric: Accuracy (%; four-way Chinese regional cuisine, chance 25). Source: arxiv.org. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 56.1 |
| 2 | Kimi K2.6 | 56.1 |
| 3 | GPT-5.1 | 48.9 |
| 4 | Qwen 3.6 Plus | 44.2 |
| 5 | GPT-5 Mini | 43.4 |
| 6 | Qwen 3.5 35B A3B | 43.4 |
| 7 | GPT-5 Nano | 42.9 |
| 8 | Gemma 4 26B A4B (IT) | 38.1 |
Interactive version: theaggregate.ai/benchmark?slug=culturalmenubench-sub-region-classification · How It Works · Data refreshed daily, snapshot 2026-09-19.