{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-09-23-drivingbench-llms-drive-real-car/","md":"https://postcutoff.com/e/2026-09-23-drivingbench-llms-drive-real-car/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-23-drivingbench-llms-drive-real-car","date":"2026-09-23","date_precision":"day","short_title":"DrivingBench: GPT-6 Astra is the first frontier LLM to complete a cone course driving a real Toyota Corolla","deck":null,"takeaway":"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.","category":"benchmark","category_label":"Benchmarks","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":[{"n":1,"title":"DrivingBench","url":"https://drivingbench.com/","type":"official","group":"primary","domain":"drivingbench.com"},{"n":2,"title":"Hacker News: GPT-6 Astra has gained the ability to drive a car (316 points)","url":"https://news.ycombinator.com/item?id=49817404","type":"discussion","group":"reactions","domain":"news.ycombinator.com"}],"official":1,"filed":"2026-09-30","updated":"2026-09-30","orgs":["OpenAI"],"title":"DrivingBench: GPT-6 Astra is the first frontier LLM to complete a cone course driving a real Toyota Corolla","summary":"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)"],"key_numbers":[],"tags":["benchmark","embodied","driving","gpt-6-astra","agents","tool-use"],"science":null,"body_md":"## What happened\n\nA three-person team wired a production car to an LLM tool interface and asked general-purpose models, without driving-specific training, to steer\naround cones. Only GPT-6 Astra finished. The site does not give a run date; the date here is the HN post.\n\n## Why it matters\n\nA small but vivid probe of general models' embodied, closed-loop control. It shows a jump between model generations, and also how far such\nmodels are from real-time driving.","disputed":[],"related":[{"id":"2026-09-03-gpt-6-astra","url":"https://postcutoff.com/e/2026-09-03-gpt-6-astra/","date":"2026-09-03","date_precision":"day","short_title":"OpenAI releases GPT-6 Astra, its first GPT-6 model","deck":null,"takeaway":"Astra is the first GPT-6-generation model and the first frontier release after the Hugging Face sandbox-escape incident and OpenAI's August training pause.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":20,"official":11,"filed":"2026-09-29","updated":"2026-10-19","orgs":["OpenAI"]},{"id":"2026-09-01-claude-fable-5-1-mythos-5-1","url":"https://postcutoff.com/e/2026-09-01-claude-fable-5-1-mythos-5-1/","date":"2026-09-01","date_precision":"day","short_title":"Anthropic releases Claude Fable 5.1 and Claude Mythos 5.1","deck":null,"takeaway":"Fable/Mythos 5.1 was Anthropic's capability frontier until Opus 5.5 matched it three weeks later at less than half the price.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":9,"official":5,"filed":"2026-09-29","updated":"2026-10-19","orgs":["Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-30","type":"filed","text":"Created (HN 316 points)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-30","run":null,"sources_read":null,"updated":"2026-09-30","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":115,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":85,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":176,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":115,"in_training_data":false}],"short_url":null}