VehicleArena - Basic Driving: leaderboard

Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.

Top models

#ModelScoreOverall rank
1DeepSeek V4.1 Flash (Max)85#35 (DeepSeek V4.1 Flash)
2Qwen 3.8 Max (xHigh)83.1#28 (Qwen 3.8 Max)
3GPT-5.6 Sol (High)82.5#18 (GPT-5.6 Sol)
4Qwen 3.8 27B (xHigh)79.6#95 (Qwen 3.8 27B)
5Kimi K3 (Max)78.9#27 (Kimi K3)
6GLM-5.3 Flash (Max)78.6#62 (GLM-5.3 Flash)
7Qwen 3 VL 32B Instruct49.3#278
8Qwen 3 VL 8B Instruct39.7#406

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=vehiclearena-basic-driving · How It Works · Data refreshed daily, snapshot 2026-10-13.