Claude Opus 5: same price, thinking-on by default, and mostly worth it
Claude Opus 5 keeps Opus 4.8 pricing and genuinely improves multi-file code refactors, but thinking-on by default quietly inflates your token bill 2-3x.
Posts tagged benchmarks
GLM-5.2 is now the open-weight model you benchmark your coding agent against
Z.ai's GLM-5.2 tops mid-July open-weight leaderboards with MIT license, 1M context, and ~91 GPQA — here's what that means for shipping a coding agent.
I Benchmarked Three Embedding Models on 50k Support Tickets
text-embedding-3-small, nomic-embed-text, and bge-m3 — same 50k tickets, same retrieval eval. The winner surprised me.