GeoDrive-Bench (Reasoning): leaderboard
Metric: Overall accuracy (%) on 5,053 human-validated multiple-choice questions on driving scenes from China, the US, the UK, Japan, Singapore and India (perception, prediction, planning and region-rule reasoning), without country labels; Reasoning prompting (a four-step free-form chain of thought: geographic inference, cultural rule recall, visual reasoning, answer selection); vLLM inference, 512 output tokens; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 12B | 58.5 |
| 2 | InternVL3-8B | 57.4 |
| 3 | InternVL3.5-8B | 54.6 |
| 4 | Qwen 2.5 VL 7B Instruct | 51.8 |
Interactive version: theaggregate.ai/benchmark?slug=geodrive-bench-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.