--- id: "2026-09-23-drivingbench-llms-drive-real-car" url: "https://postcutoff.com/e/2026-09-23-drivingbench-llms-drive-real-car/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-23" date_precision: day category: benchmark importance: 2 confidence: medium status: [Partly confirmed] sources: 2 editor: human editor human_review: null version: "2026-10-04" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-23-drivingbench-llms-drive-real-car/ # DrivingBench: GPT-6 Astra is the first frontier LLM to complete a cone course driving a real Toyota Corolla DrivingBench, published around Sept 23, 2026 by Aditya Ramabadran, Simon Mahns and Tobias Gessler, gives frontier LLMs out-of-the-box control of a real Toyota Corolla's steering, accelerator and brakes through tool calls and scores them on a fixed cone course. GPT-6 Astra finished the course (5 min 22 s, on its second attempt); Claude Fable 5.1, Grok 4.6 and GPT-5.6 Sol reached only 6–11% of the course. ## Key facts - Setup: models control steering, accelerator and brakes of a Toyota Corolla via tool calls; up to three attempts per model in one continuous conversation; ranked by best attempt - GPT-6 Astra: 49% progress then a collision on attempt 1; 100% in 5:22 on attempt 2 - Other models (Claude Fable 5.1, Grok 4.6, GPT-5.6 Sol): at most 6–11% progress, mostly DNF - Very low speeds for safety; latency was 'one of the biggest issues'; each tool output carries a timestamp so the model can learn its own latency in context (authors on HN) - Authors call it 'just sort of a fun benchmark ... probably not actually practical any time soon' - Per HN discussion the course is ~135 m and the Astra run cost roughly $8 in API tokens (not stated on the site) ## What happened A three-person team wired a production car to an LLM tool interface and asked general-purpose models, without driving-specific training, to steer around cones. Only GPT-6 Astra finished. The site does not give a run date; the date here is the HN post. ## Why it matters A small but vivid probe of general models' embodied, closed-loop control. It shows a jump between model generations, and also how far such models are from real-time driving. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 115 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 85 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 176 days after its cutoff - Grok 4.7 (training cutoff May 2026): 115 days after its cutoff ## Sources 1. [DrivingBench](https://drivingbench.com/) (drivingbench.com, official) 2. [Hacker News: GPT-6 Astra has gained the ability to drive a car (316 points)](https://news.ycombinator.com/item?id=49817404) (news.ycombinator.com, discussion) ## Changes - 2026-09-30 (filed): Created (HN 316 points) ## Related - 2026-09-03: [OpenAI releases GPT-6 Astra, its first GPT-6 model](https://postcutoff.com/e/2026-09-03-gpt-6-astra/index.md) - 2026-09-01: [Anthropic releases Claude Fable 5.1 and Claude Mythos 5.1](https://postcutoff.com/e/2026-09-01-claude-fable-5-1-mythos-5-1/index.md)