Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Browser Agent Benchmark: Comparing LLM models for web automation

browser-use.com

Post reply on HN
Print view View original

1–7 of 7 posts

Re: Browser Agent Benchmark: Comparing LLM models for web automation

#6

Post by pixel_popping »

djohnston wrote: post #5
pixel_popping wrote: post #3

It's lacking the best model (Opus 4.5) on the benchmark tho.

Yeah but then their own product might not score the highest.

Exactly why I'm pointing it out, which feels a bit corrupt, but understandable.

Re: Browser Agent Benchmark: Comparing LLM models for web automation

#7

Post by djohnston »

pixel_popping wrote: post #6
djohnston wrote: post #5

Earlier quoted context omitted.

Yeah but then their own product might not score the highest.

Exactly why I'm pointing it out, which feels a bit corrupt, but understandable.

tbh i was a bit cranky yesterday - even if they are #2 on a legit benchmark that would be impressive
Post reply on HN