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

#ModelScoreOverall rank
1Qwen 2.5 VL 72B Instruct63#849
2Intern-S160.8#627
3GPT-5 Mini (2025-08-07)46.4#352
4Gemini 2.5 Pro45.3#280
5Qwen 3.5 Plus44.5#250
6Intern-S1-mini41.9#1186
7Qwen 3 VL 30B A3B Instruct40.8#903
8GPT-5.238.5#190
9Qwen3-VL-Flash27.8#734
10Gemini 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.