FAM-Bench - Comparative Ranking (Knowledge Injection): leaderboard
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 2031. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 39.8 |
| 2 | GPT-5.4 | 36.9 |
| 3 | Claude Sonnet 4.6 | 35.1 |
| 4 | Gemma 3 12B (IT) | 32.3 |
| 5 | Qwen 3 VL 8B Instruct | 31.8 |
Interactive version: theaggregate.ai/benchmark?slug=fam-bench-comparative-ranking-knowledge-injection · How It Works · Data refreshed daily, snapshot 2026-10-07.