OmniTraffic - Special Vehicle Recognition: leaderboard
An OmniTraffic task: special vehicle recognition (detect and classify police cars, ambulances and fire trucks). OmniTraffic (2026) renders reconstructed real intersections as controllable 3D scenes and adds real roadside footage; accuracy in percent, higher is better.
Metric: Accuracy (%) on special vehicle recognition (detect and classify police cars, ambulances and fire trucks), multiple-choice VQA on the 3,204-item human-verified OmniTraffic test set (12 reconstructed simulated intersections plus real roadside surveillance from South Korea and Tianjin), greedy decoding (at most 500 tokens), exact match against the answer letter with up to three attempts for invalid output (still invalid counts as wrong); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 88.2 | #137 |
| 2 | GPT-5.2 | 78.5 | #176 |
| 3 | Grok 4 | 78.5 | #307 |
| 4 | GPT-4o | 76.5 | #741 |
| 5 | Gemini 2.5 Pro | 72.8 | #266 |
| 6 | Qwen 3 VL 235B A22B (Thinking) | 67.9 | #451 |
| 7 | Claude Sonnet 4.5 (Thinking) | 56.7 | #250 (Claude Sonnet 4.5) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=omnitraffic-special-vehicle-recognition · How It Works · Data refreshed daily, snapshot 2026-11-13.