FAM-Bench - Comparative Ranking (Baseline): leaderboard

Comparative dish ranking in FAM-Bench (2026), a food-as-medicine benchmark: given a health condition and four candidate dishes with recipe text and images, the model ranks them by suitability, under the Baseline prompting mode, in which the model answers directly. The score is top-1 accuracy in percent, chance 25; higher is better.

Metric: Top-1 accuracy (%) on Task 2: rank four candidate dishes for a health condition and match the gold most suitable dish, Baseline prompting mode (the model answers directly), 1,000 comparative queries over four candidate dishes with recipe text and image, 13 health conditions, nutrition-expert verified, greedy decoding with JSON output; chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around 2032. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro32.7#276
2GPT-5.432.1#135
3Qwen 3 VL 8B Instruct31.3#1029
4Claude Sonnet 4.630.9#173
5Gemma 3 12B (IT)30.6#1887

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=fam-bench-comparative-ranking-baseline · How It Works · Data refreshed daily, snapshot 2026-11-21.