I Spent 400M Tokens Testing Kimi K3.1 — the Open-Source King Still Needs Work
I Spent 400M Tokens Testing Kimi K3.1 — the Open-Source King Still Needs Work Last weekend Kimi K3.1 Pro dropped, and honestly I was hyped. The last K3 I touche
OpenAI's strongest model — 1M context
“Astra is terrible with thinking. Sol 6.1 is better for anything that requires thought. ... Astra is an implementation model.”
“Just used it to review a bunch of architecture. Very strong performer.”
“Quite honestly 6-Astra has disappointed ever since Opus 5.5. It makes assumptions without clarification, burns through weekly quotas and just feels slower and more clunky.”
Yes — GPT-6 Astra has a 57% worth-it score, based on 314 community votes.
GPT-6 Astra is a Chat model. Most capable model I've used this year, period. The 1M context actually works for huge codebases
$10/$50 per 1M tokens
I Spent 400M Tokens Testing Kimi K3.1 — the Open-Source King Still Needs Work Last weekend Kimi K3.1 Pro dropped, and honestly I was hyped. The last K3 I touche
I’ve used ChatGPT while developing MaestroGrade, a music-teaching project, and while preparing scripts and explanations for DRS Automation Services. My most use
Codex right now feels dumb and lazy Compared to how blown away I was when 5.5 first dropped, 6 / 6.1 is honestly a big step down. The only time I get that old "