DiningBench - Fine-Grained Classification: leaderboard
DiningBench (2026) evaluates vision-language models on multi-view user photos of restaurant dishes, testing dish classification against same-menu distractors, nutrition estimation and food visual question answering. This board is accuracy in percent at picking the dish among eight candidates from the same menu; higher is better.
Metric: Accuracy (%) choosing the dish among eight same-menu candidates (seven hard distractors) from multi-view user photos, over the 2,884 DiningBench classification samples; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 29 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 81.83 | #156 |
| 2 | Gemini 3 Pro (Preview) | 81.55 | #123 |
| 3 | Gemini 2.5 Pro | 73.51 | #280 |
| 4 | Gemini 2.5 Flash | 71.01 | #466 |
| 5 | GPT-5 | 70.18 | #185 |
| 6 | GPT-4.1 | 68.59 | #506 |
| 7 | Qwen 3 VL 30B A3B Instruct | 65.43 | #903 |
| 8 | Qwen 2.5 VL 72B Instruct | 65.29 | #849 |
| 9 | GPT-4o | 65.26 | #754 |
| 10 | O4 Mini | 64.81 | #372 |
| 11 | Qwen 3 VL 8B Instruct | 64.15 | #1043 |
| 12 | Qwen 3 VL 30B A3B (Thinking) | 61.34 | #727 |
| 13 | Qwen 2.5 VL 32B Instruct | 61.17 | #1065 |
| 14 | Qwen 2.5 VL 7B Instruct | 60.85 | #1919 |
| 15 | Qwen 3 VL 4B Instruct | 60.06 | #1348 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=diningbench-fine-grained-classification · How It Works · Data refreshed daily, snapshot 2026-11-22.