OmniFood-Bench - Cooking Method (Restaurant Food): leaderboard

Metric: Cooking-method accuracy (%; share of Restaurant 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 March 2027. 6 models tracked.

Top models

#ModelScore
1GPT-5.175.81
2Gemini 3 Flash69.35
3Claude Sonnet 467.57
4InternVL3.5-8B67.45

Interactive version: theaggregate.ai/benchmark?slug=omnifood-bench-cooking-method-restaurant-food · How It Works · Data refreshed daily, snapshot 2026-09-29.