OmniFood-Bench - Nutritional Profile (Restaurant Food): leaderboard
Metric: Nutritional-profile MAPE (%; mean absolute percentage error of the predicted macronutrient grams of Restaurant Food images, lower is better and unbounded above; images of the MM-Food-100K subset; zero-shot, one standardized prompt per task; the open-weight models see all 1,208 samples and the proprietary models a 496-sample subset). Source: arxiv.org. Saturation forecast: Around April 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 40.89 |
| 2 | InternVL3.5-8B | 49.32 |
| 3 | Claude Sonnet 4 | 49.99 |
| 4 | Gemini 3 Flash | 71.12 |
Interactive version: theaggregate.ai/benchmark?slug=omnifood-bench-nutritional-profile-restaurant-food · How It Works · Data refreshed daily, snapshot 2026-09-29.