V2X-QA - RSU Long-Range Cues: 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 far-field cues. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the infrastructure-side RSU Long-Range Cues task (IS4); 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 3 VL 30B A3B Instruct53.2#895
2Gemini 2.5 Pro51.7#276
3GPT-5.247.5#185
4Qwen3-VL-Flash47.2#728
5Qwen 2.5 VL 72B Instruct46#841
6GPT-5 Mini (2025-08-07)45.3#345
7Intern-S1-mini41.1#1178
8Qwen 3.5 Plus39.6#242
9Intern-S134.3#624
10Gemini 3 Flash (Preview)11.7#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-rsu-long-range-cues · How It Works · Data refreshed daily, snapshot 2026-11-21.