V2X-QA - RSU Global Risk: leaderboard
Metric: Accuracy (%) on the infrastructure-side RSU Global Risk task (IS3); 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 2.5 VL 72B Instruct | 63 |
| 2 | GPT-5 Mini | 46.4 |
| 3 | Gemini 2.5 Pro | 45.3 |
| 4 | Qwen 3.5 Plus | 44.5 |
| 5 | Qwen 3 VL 30B A3B Instruct | 40.8 |
| 6 | GPT-5.2 | 38.5 |
| 7 | Gemini 3 Flash (Preview) | 20.8 |
Interactive version: theaggregate.ai/benchmark?slug=v2x-qa-rsu-global-risk · How It Works · Data refreshed daily, snapshot 2026-10-07.