OmniTraffic - Temporal Reasoning: leaderboard
An OmniTraffic task: temporal reasoning (order frames and track queues over time). OmniTraffic (2026) renders reconstructed real intersections as controllable 3D scenes and adds real roadside footage; accuracy in percent, higher is better.
Metric: Accuracy (%) on temporal reasoning (order frames and track queues over time), 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: Not forecast. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4 | 56.4 | #307 |
| 2 | Claude Sonnet 4.5 (Thinking) | 54.9 | #250 (Claude Sonnet 4.5) |
| 3 | Qwen 3 VL 235B A22B (Thinking) | 50.5 | #451 |
| 4 | Gemini 3 Pro | 48.9 | #137 |
| 5 | GPT-4o | 48.7 | #741 |
| 6 | GPT-5.2 | 43 | #176 |
| 7 | Gemini 2.5 Pro | 22.8 | #266 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=omnitraffic-temporal-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-13.