V2X-QA - Infrastructure-Side Average: 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 mean accuracy of the four roadside-unit tasks. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the infrastructure-side (roadside unit) view, mean of its four tasks; 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 Instruct59.7#841
2Intern-S159.7#624
3Qwen3-VL-Flash54.7#728
4Qwen 3 VL 30B A3B Instruct50.9#895
5GPT-5.249.6#185
6Qwen 3.5 Plus48.5#242
7Intern-S1-mini48.5#1178
8GPT-5 Mini (2025-08-07)47.4#345
9Gemini 2.5 Pro41.1#276
10Gemini 3 Flash (Preview)35.3#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-infrastructure-side-average · How It Works · Data refreshed daily, snapshot 2026-11-21.