CrossVid - Comparative Culinary QA: leaderboard
Open-ended answers comparing cooking videos, scored by GPT-4.1 for coverage and correctness of the reference key points; unlike the other CrossVid boards, no answer options are given.
Metric: Judge score (%). Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 59.8 | #274 |
| 2 | Qwen 2.5 VL 32B Instruct | 41.2 | #1074 |
| 3 | Kimi-VL-A3B (Thinking) | 29.2 | |
| 4 | GLM-4.1V-9B (Thinking) | 26.9 | |
| 5 | InternVL3-78B | 23.2 | #755 |
| 6 | LLaVA-Video-72B-Qwen2 | 17.8 | #1344 |
| 7 | InternVL3-38B | 16.2 | #927 |
| 8 | Qwen2.5-Omni-7B | 15.3 | #1883 |
| 9 | Qwen 2.5 VL 7B Instruct | 12 | #1893 |
| 10 | LongVA-7B-DPO | 10.7 | #2177 |
| 11 | VideoLLaMA3-7B | 9.8 | #2015 |
| 12 | InternVL3-8B | 9.7 | #1756 |
| 13 | MiniCPM-o-2.6 | 9 | #2417 |
| 14 | Video-R1-7B | 8 | #2053 |
| 15 | Phi-3.5-Vision Instruct | 4.3 | #6271 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=crossvid-comparative-culinary-qa · How It Works · Data refreshed daily, snapshot 2026-11-17.