FAM-Bench - Comparative Ranking (Knowledge Injection): 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 Knowledge Injection prompting mode, in which condition-specific dietary rules are added to the prompt. 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, Knowledge Injection prompting mode (condition-specific dietary rules are added to the prompt), 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 2030. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro39.8#276
2GPT-5.436.9#135
3Claude Sonnet 4.635.1#173
4Gemma 3 12B (IT)32.3#1887
5Qwen 3 VL 8B Instruct31.8#1029

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-knowledge-injection · How It Works · Data refreshed daily, snapshot 2026-11-21.