OmniFood-Bench - Cooking Method (Homemade Food): leaderboard
OmniFood-Bench asks vision-language models to classify how a pictured food was prepared, which is what caloric reasoning downstream depends on. This board covers images of home-cooked dishes and is scored as classification accuracy.
Metric: Cooking-method accuracy (%; share of Homemade Food images whose preparation technique the model classifies correctly; 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 February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 79.06 | #229 |
| 2 | Gemini 3 Flash | 73.93 | #164 |
| 3 | Claude Sonnet 4 | 65.11 | #400 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=omnifood-bench-cooking-method-homemade-food · How It Works · Data refreshed daily, snapshot 2026-11-13.