GeoDrive-Bench: 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; Direct prompting (the model answers with a letter in one pass, no intermediate reasoning); vLLM inference, 512 output tokens; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-8B | 61 |
| 2 | Gemma 3 12B | 60.1 |
| 3 | InternVL3.5-8B | 59.9 |
| 4 | Qwen 2.5 VL 7B Instruct | 57.9 |
Interactive version: theaggregate.ai/benchmark?slug=geodrive-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.