V2X-QA - Cooperative Scene Understanding: leaderboard
Metric: Accuracy (%) on the cooperative Scene Understanding task (CO1); four-option multiple-choice questions on the expert-verified test split, answered as a single option letter under the paper's unified prompt; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 86 |
| 2 | Qwen 2.5 VL 72B Instruct | 61.9 |
| 3 | Qwen 3.5 Plus | 37.7 |
| 4 | GPT-5.2 | 34 |
| 5 | GPT-5 Mini | 26.4 |
| 6 | Qwen 3 VL 30B A3B Instruct | 20.8 |
| 7 | Gemini 2.5 Pro | 15.8 |
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-cooperative-scene-understanding · How It Works · Data refreshed daily, snapshot 2026-10-07.