CrossVid: leaderboard
Each model answers questions that require comparing or combining several videos at once (ten tasks; 9,015 questions over 5,331 videos); the score is the source's mean accuracy over the ten tasks. Single-video benchmarks such as Video-MME ask about one clip.
Metric: Overall accuracy (%). Source: raw.githubusercontent.com. Saturation forecast: Around February 2027. 15 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 50.4 | #274 |
| 2 | GLM-4.1V-9B (Thinking) | 35.1 | |
| 3 | Qwen 2.5 VL 32B Instruct | 33.7 | #1074 |
| 4 | Kimi-VL-A3B (Thinking) | 28.2 | |
| 5 | LLaVA-Video-72B-Qwen2 | 27.5 | #1344 |
| 6 | InternVL3-78B | 25.8 | #755 |
| 7 | InternVL3-8B | 25.6 | #1756 |
| 8 | MiniCPM-o-2.6 | 25.6 | #2417 |
| 9 | Qwen2.5-Omni-7B | 24.6 | #1883 |
| 10 | InternVL3-38B | 23.5 | #927 |
| 11 | Video-R1-7B | 21.6 | #2053 |
| 12 | Phi-3.5-Vision Instruct | 21.5 | #6271 |
| 13 | Qwen 2.5 VL 7B Instruct | 18.3 | #1893 |
| 14 | LongVA-7B-DPO | 18 | #2177 |
| 15 | VideoLLaMA3-7B | 15.3 | #2015 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=crossvid · How It Works · Data refreshed daily, snapshot 2026-11-17.