V2X-QA - Cooperative Visibility: 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 what each view can and cannot see. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the cooperative Visibility task (CO2); 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
1Intern-S170.2#624
2Gemini 2.5 Pro59.2#276
3Qwen 2.5 VL 72B Instruct54.7#841
4Qwen3-VL-Flash47.9#728
5GPT-5.236.2#185
6Qwen 3 VL 30B A3B Instruct32.1#895
7Qwen 3.5 Plus30.9#242
8Intern-S1-mini29.1#1178
9GPT-5 Mini (2025-08-07)9.8#345
10Gemini 3 Flash (Preview)3.8#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-cooperative-visibility · How It Works · Data refreshed daily, snapshot 2026-11-21.