V2X-QA - Cooperative Scene Understanding: 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 cooperative task on grounding one scene across both views. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the cooperative Scene Understanding task (CO1); 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: Around February 2027. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash (Preview)86#152
2Intern-S1-mini64.5#1178
3Qwen 2.5 VL 72B Instruct61.9#841
4Intern-S157.4#624
5Qwen 3.5 Plus37.7#242
6GPT-5.234#185
7GPT-5 Mini (2025-08-07)26.4#345
8Qwen3-VL-Flash22.3#728
9Qwen 3 VL 30B A3B Instruct20.8#895
10Gemini 2.5 Pro15.8#276

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-cooperative-scene-understanding · How It Works · Data refreshed daily, snapshot 2026-11-21.