V2X-QA - Ego Risk: leaderboard
V2X-QA (2026) asks multimodal models four-option driving questions about real vehicle-mounted and roadside camera views of the same scenes, answered with one option letter on the expert-verified test split. This board is the vehicle-side task on localized safety risks. Accuracy in percent; higher is better.
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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 51.3 | #841 |
| 2 | Qwen 3.5 Plus | 44.5 | #242 |
| 3 | Intern-S1 | 42.3 | #624 |
| 4 | Gemini 2.5 Pro | 40.4 | #276 |
| 5 | Qwen3-VL-Flash | 39 | #728 |
| 6 | GPT-5 Mini (2025-08-07) | 32.1 | #345 |
| 7 | Intern-S1-mini | 29.8 | #1178 |
| 8 | Qwen 3 VL 30B A3B Instruct | 27.5 | #895 |
| 9 | GPT-5.2 | 26 | #185 |
| 10 | Gemini 3 Flash (Preview) | 20.8 | #152 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-ego-risk · How It Works · Data refreshed daily, snapshot 2026-11-21.