FoodMonitor: leaderboard
FoodMonitor (2026) asks multimodal models to find food-safety violations in 477 one-minute commercial kitchen videos against a 27-item rule document, naming the rule, describing the violation and, for workers, tracking the person with boxes over time. The C score, 0 to 100 and higher is better, averages the detection F1 for environment and for person violations.
Metric: C score (0-100; the paper's 0-1 score times 100): the mean of the environment-violation F1 and the person-violation F1, on the 477 one-minute FoodMonitor kitchen surveillance clips (3,307 annotated violations of a 27-item food safety rule document), frames at 1 fps plus the full rule document, structured JSON output; a prediction counts only if its rule category matches and a text comparison model accepts its description as the same violation, one-to-one; person violations must first localize the worker with at least ten box-and-time anchors (mean IoU 0.3, coverage 0.6); all models in thinking mode; higher is better. Source: arxiv.org. Saturation forecast: Around July 2028. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Seed 2.0 Pro | Thinking | 36 | #226 |
| 2 | Gemini 3 Flash | 31.6 | #180 | |
| 3 | Doubao Seed 2.0 Lite | Thinking | 29.8 | #204 |
| 4 | GLM-4.6V | 27.9 | #721 | |
| 5 | Gemini 3 Pro | 25 | #146 | |
| 6 | Qwen 3.5 397B A17B | 23.1 | #270 | |
| 7 | Kimi K2.5 | 20.8 | #272 | |
| 8 | Qwen 3 VL 235B A22B (Thinking) | 19.3 | #462 | |
| 9 | GLM-4.6V-Flash | 13.5 | #1049 | |
| 10 | MiMo-VL-7B-RL | 13.2 | #1160 | |
| 11 | Qwen 3 VL 8B (Thinking) | 13 | #924 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=foodmonitor · How It Works · Data refreshed daily, snapshot 2026-11-22.