DiningBench - Carbohydrate Estimation: 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 the mean absolute percentage error of the estimated carbohydrates; lower is better.
Metric: Mean absolute percentage error (%) of the estimated carbohydrates over the 1,650 DiningBench nutrition-estimation dishes (multi-view restaurant photos; ground truth from merchant labels or ingredient-based estimates cross-checked against USDA FoodData Central); lower is better. Source: arxiv.org. Saturation forecast: Around March 2027. 29 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 27.4 | #119 |
| 2 | Gemini 3 Flash (Preview) | 27.94 | #152 |
| 3 | GPT-4.1 | 35.81 | #505 |
| 4 | GPT-5 | 36.63 | #178 |
| 5 | O4 Mini | 37.38 | #368 |
| 6 | GPT-4o | 40.19 | #751 |
| 7 | Qwen 3 VL 30B A3B Instruct | 41.53 | #895 |
| 8 | Qwen 2.5 VL 72B Instruct | 41.7 | #841 |
| 9 | Gemini 2.5 Flash | 42.62 | #463 |
| 10 | Gemini 2.5 Pro | 43.01 | #276 |
| 11 | Qwen 2.5 VL 32B Instruct | 43.92 | #1062 |
| 12 | Qwen 3 VL 8B Instruct | 43.99 | #1029 |
| 13 | GPT-4o Mini | 45.03 | #1667 |
| 14 | Qwen 3 VL 30B A3B (Thinking) | 48.12 | #719 |
| 15 | MiMo-VL-7B-RL | 48.24 | #1155 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=diningbench-carbohydrate-estimation · How It Works · Data refreshed daily, snapshot 2026-11-21.