V2X-QA - Cooperative Prediction: 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 short-horizon prediction from both views. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the cooperative Prediction task (CO3); 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 October 2028. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3.5 Plus64.5#250
2Qwen 3 VL 30B A3B Instruct52.1#903
3GPT-5.249.4#190
4GPT-5 Mini (2025-08-07)47.2#352
5Gemini 2.5 Pro45.3#280
6Qwen3-VL-Flash44.9#734
7Gemini 3 Flash (Preview)43.4#156
8Intern-S1-mini43.4#1186
9Intern-S143#627
10Qwen 2.5 VL 72B Instruct42.6#849

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-cooperative-prediction · How It Works · Data refreshed daily, snapshot 2026-11-22.