UltraVR - CCTV: leaderboard
The CCTV domain of UltraVR (2026): comparison, logical verification and relational questions about people and vehicles in crowded wide-field surveillance frames, four-choice. Models answer directly from the original ultra-resolution image under their own preprocessing; accuracy in percent, higher is better.
Metric: Accuracy (%) on the CCTV surveillance domain (comparison, logical verification and relational inference over people and vehicles in crowded wide-field scenes), direct answering (S0) with the original ultra-resolution image under each model default preprocessing (V2); four-choice questions except anomaly detection, which asks for the grid coordinate of the one anomalous cell out of 100; higher is better. Source: arxiv.org. Saturation forecast: Around July 2028. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 51.8 | #49 |
| 2 | Gemma 4 26B | 48.2 | #612 |
| 3 | Gemini 3.1 Pro (Preview) | 46.5 | #94 |
| 4 | GPT-5.4 | 37.7 | #123 |
| 5 | GLM-4.5V | 35.8 | #744 |
| 6 | Qwen 3.5 27B | 31.6 | #359 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ultravr-cctv · How It Works · Data refreshed daily, snapshot 2026-11-13.