Y
Hacker News
new
|
ask
|
show
|
jobs
by
numbers
55 days ago
I've stopped trusting these "trust me bro" benchmarks and just started going to LM Arena and looking for the actual benchmark comparisons.
https://arena.ai/leaderboard/code
2 comments
stri8ted
55 days ago
I doubt this is representative of real world usage. There is a difference between a few turns on a web chatbot, vs many-turn cli usage on a real project.
link
nba456_
55 days ago
This is not any better of a benchmark
link