Re:$500 GPU outperforms Claude Sonnet on coding benchmarks
by smokel on Friday March 27, 2026 @04:40AM
(#47540298)
And what tooling do you use with that? In my experience, there is quite a bit of difference between using, say, OpenCode, or the commercial offerings.
Re:$500 GPU outperforms Claude Sonnet on coding benchmarks
by moffkalast on Friday March 27, 2026 @04:43AM
(#47540311)
No tooling, just manual use. When doing these comparisons I gather and format all the data they need to figure out the problem, and paste the same thing into all models so it's a pretty even eval.
I doubt Kimi would do well with most harnesses, its outputs are pretty chaotic in terms of formatting but the inteligence is definitely there.
It does have some kind of horrible context consistency problem though, if you ask it to rewrite something verbatim it'll inject tiny random changes everywhere and potentially break it. That's something that other SOTA models haven't done for at least two years now and is a real problem. I can't trust it to do a full rewrite, just diffs.