V2X-QA - Ego Risk: leaderboard
Metric: Accuracy (%) on the vehicle-side Ego Risk task (VS3); 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: Not forecast. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 51.3 |
| 2 | Qwen 3.5 Plus | 44.5 |
| 3 | Gemini 2.5 Pro | 40.4 |
| 4 | GPT-5 Mini | 32.1 |
| 5 | Qwen 3 VL 30B A3B Instruct | 27.5 |
| 6 | GPT-5.2 | 26 |
| 7 | Gemini 3 Flash (Preview) | 20.8 |
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-ego-risk · How It Works · Data refreshed daily, snapshot 2026-10-07.