Claude vs. DeepSeek vs. GLM: what coding agents pick

A same-prompt comparison of coding agents run through OpenCode found that Claude Code and the free models DeepSeek V4.1 Flash and GLM 5.3 Flash agreed on the top pick in only 2 of 6 category-and-stack pairs, with Python deployment runs choosing Heroku 14 of 30 times versus 0 of 29 on Next.js. Claude picked Drizzle ORM in 12 of 18 Next.js runs and SQLAlchemy in 18 of 18 Python runs, while Next.js email choices split toward Resend (16 of 30) and Python toward raw SMTP (27 of 29). The author cautions the samples are small — 18 Claude runs per category per stack (6 each for Opus 5.5, Sonnet 5.5 and Haiku 5.5) against 6 runs each for DeepSeek and GLM — and should be read as a lead.

heroku only shows up on python, for every model Next.js 0 heroku - Claude0/18 - DeepSeek0/5 - GLM0/6 Python 14 heroku - Claude7/18 - DeepSeek3/6 - GLM4/6 same prompts, claude code next to two free models in opencode. same top pick in 2 of 3 on python, in 0 of 3 on next.js. 16 resend raw smtp 27/29 Opus 5.5, Sonnet 5.5, Haiku 5.5 via opencode splits highlighted one bar per model per stack. thin bars are single claude models. Next.js + TypeScript Python + FastAPI same top pick in 2 of 6 category and stack pairs. 14 of 30 Python deploy runs picked heroku. Next.js 0 of 29. Next.js: resend 16 of 30. Python: resend 0, raw smtp 27 of 29. ORM on Next.js: Claude drizzle orm 12 of 18, DeepSeek drizzle orm / prisma 2 of 6, GLM drizzle orm 5 of 6. on Python: Claude sqlalchemy 18 of 18, DeepSeek sqlalchemy 6 of 6, GLM sqlalchemy 4 of 5. deployment on Next.js: Claude plain docker 14 of 18, DeepSeek fly.io / plain docker 2 of 5, GLM built its own / plain docker 3 of 6. on Python: Claude heroku / plain docker 7 of 18, DeepSeek heroku 3 of 6, GLM heroku 4 of 6. email on Next.js: Claude resend 11 of 18, DeepSeek raw smtp / resend 3 of 6, GLM raw smtp 4 of 6. on Python: Claude raw smtp 17 of 18, DeepSeek raw smtp 5 of 5, GLM raw smtp 5 of 6. claude code: 18 runs per category per stack opus 5.5, sonnet 5.5, haiku 5.5, 6 each . DeepSeek V4.1 Flash: 6, GLM 5.3 Flash: 6, run through OpenCode on the free tier. same prompts, same starters, same detector. small samples, read them as a lead.