News for hackers. Stuff that matters.
Re:Happy 10k Day by nomilk on Wednesday March 12, 2025 @12:11AM (#43339890)
Are there any reliable sites for ranking and benchmarking self-driving capabilities? (i.e. similar to what WebDev Arena and SWE-bench do for LLMs).

Curious where telsa and comma rank, and where others (e.g. mercedes) rank comparatively.

Re:Happy 10k Day by granolatron on Wednesday March 12, 2025 @01:23AM (#43340210)
https://data.consumerreports.org/wp-content/uploads/2020/11/...

They’ve done updates each year since but haven’t included comma for some reason.

Re:Happy 10k Day by darknavi on Wednesday March 12, 2025 @01:42AM (#43340267)
Doesn't that file list them at the top?

> Comma Two > Open Pilot

Re:Happy 10k Day by nomilk on Wednesday March 12, 2025 @01:58AM (#43340321)
Report looks great, but it's ~5 years old.