Posts tagged "benchmarks" — Broke It

Muse Code's 82.9% on Terminal-Bench 2.1: what a 4-point gap costs you in a real repo

Meta Superintelligence Labs shipped Muse Code, a terminal coding agent scoring 82.9% on Terminal-Bench 2.1 — here's what its 4-point gap to Claude Opus 5 actually costs.

model-releasefrontier-modelscoding

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.

open-sourcemodelslocalllama

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.

embeddingsragvector-db

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.

Posts tagged benchmarks

Muse Code's 82.9% on Terminal-Bench 2.1: what a 4-point gap costs you in a real repo

Claude Opus 5: same price, thinking-on by default, and mostly worth it

GLM-5.2 is now the open-weight model you benchmark your coding agent against

I Benchmarked Three Embedding Models on 50k Support Tickets