Kimi K3 ranks #6 on ReactBench
- It performs better than Opus 4.8 while being over 2x cheaper (!!)
- Scores 33%, jump of +10% compared to K2.7
- Lags behind the frontier (Fable and Sol) in frontend production-readiness:
Kimi K3 ranks #6 on ReactBench
- It performs better than Opus 4.8 while being over 2x cheaper (!!)
- Scores 33%, jump of +10% compared to K2.7
- Lags behind the frontier (Fable and Sol) in frontend production-readiness:
If you're a React dev:
- GPT 5.6 Sol xhigh performs the overall the best
- GPT 5.6 Terra medium is the most bang for your buck
Claude Fable 5 performs on par with Sol but is on average 6x more expensive!
https://t.co/Cjmm8Dh8Oj rules are now in the React, Next.js and TanStack presets for ESLint and Oxlint!
The useful stuff: fewer unnecessary effects, better render performance checks, hydration catches, server component rules, security checks and framework-specific diagnostics.
Thanks a million, @milliondotjs 🙌
React Doctor v2 is here
Your agent writes bad React code, this catches it
Works with Next.js, Vite, React Native. Fix your app in minutes
npx react-doctor@latest
Introducing React Doctor
Scan your React codebase for anti-patterns:
- Unnecessary useEffects
- Fix accessibility issues
- Prop drilling instead of context / composition
Run as a CLI or agent skill. Repeat until passing. Fully open source
ami is now a desktop app
run parallel coding agents from your computer without breaking your flow
claude opus 4.5 is unreasonably good but the interfaces around it haven't caught up
go try it out for free :)