V2X-QA - RSU Global 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 roadside-unit task on macroscopic risk factors. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the infrastructure-side RSU Global Risk task (IS3); 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 | 63 | #849 |
| 2 | Intern-S1 | 60.8 | #627 |
| 3 | GPT-5 Mini (2025-08-07) | 46.4 | #352 |
| 4 | Gemini 2.5 Pro | 45.3 | #280 |
| 5 | Qwen 3.5 Plus | 44.5 | #250 |
| 6 | Intern-S1-mini | 41.9 | #1186 |
| 7 | Qwen 3 VL 30B A3B Instruct | 40.8 | #903 |
| 8 | GPT-5.2 | 38.5 | #190 |
| 9 | Qwen3-VL-Flash | 27.8 | #734 |
| 10 | Gemini 3 Flash (Preview) | 20.8 | #156 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-rsu-global-risk · How It Works · Data refreshed daily, snapshot 2026-11-22.