V2X-QA - RSU Long-Range Cues: leaderboard
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.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 30B A3B Instruct | 53.2 |
| 2 | Gemini 2.5 Pro | 51.7 |
| 3 | GPT-5.2 | 47.5 |
| 4 | Qwen 2.5 VL 72B Instruct | 46 |
| 5 | GPT-5 Mini | 45.3 |
| 6 | Qwen 3.5 Plus | 39.6 |
| 7 | Gemini 3 Flash (Preview) | 11.7 |
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-rsu-long-range-cues · How It Works · Data refreshed daily, snapshot 2026-10-07.