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

#ModelScore
1InternVL3-8B61
2Gemma 3 12B60.1
3InternVL3.5-8B59.9
4Qwen 2.5 VL 7B Instruct57.9

Interactive version: theaggregate.ai/benchmark?slug=geodrive-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.