How I AI
How I AI
Claire Vo
GLM 5.2: why I’m replacing Opus in Claude Code with this new model
27 minutes Posted Jun 24, 2026 at 11:00 am.
I put GLM 5.2, the open-weight coding model from Z.AI, through four real tasks inside my actual codebase: a codebase architecture audit, a UI redesign, and a 45-minute autonomous bug-hunting session pulling from Sentry and Vercel logs. Total cost: $3.36 for roughly 6 million tokens, a prioritized bug-fix dashboard I’m actually shipping from, and a landing page redesign that matched Chat PRD’s design system on the first try.What you’ll learn:What “open-weight” actually means and why it matters for cost and vendor independenceHow to connect GLM 5.2 to Cursor and Claude CodeHow it performs on codebase exploration and autonomous architecture summarization in a real production Next.js appWhether GLM 5.2 can match an existing design systemHow the model handles a 45-minute long-running autonomous taskWhere GLM 5.2 stumbled The actual cost breakdown—Brought to you by:Mercury—Radically different banking loved by over 300K entrepreneurs—In this episode, we cover:
What open-weight models are and why GLM 5.2 is worth testing
GLM 5.2 model overview
Capabilities and benchmark results
How to set up GLM 5.2 in Cursor
How to set up GLM 5.2 in Claude Code
Live test 1: codebase exploration and architecture audit on ChatPRD
Live test 2: generating an HTML architecture and roadmap page
Live test 3: redesigning the How I AI landing page in Cursor
Live test 4: 45-minute autonomous task, pulling Sentry errors and Vercel logs
Where it struggled
My verdict on the output
0:00
27:13
Download MP3
Show notes
I put GLM 5.2, the open-weight coding model from Z.AI, through four real tasks inside my actual codebase: a codebase architecture audit, a UI redesign, and a 45-minute autonomous bug-hunting session pulling from Sentry and Vercel logs. Total cost: $3.36 for roughly 6 million tokens, a prioritized bug-fix dashboard I’m actually shipping from, and a landing page redesign that matched Chat PRD’s design system on the first try.What you’ll learn:What “open-weight” actually means and why it matters for cost and vendor independenceHow to connect GLM 5.2 to Cursor and Claude CodeHow it performs on codebase exploration and autonomous architecture summarization in a real production Next.js appWhether GLM 5.2 can match an existing design systemHow the model handles a 45-minute long-running autonomous taskWhere GLM 5.2 stumbled The actual cost breakdown—Brought to you by:Mercury—Radically different banking loved by over 300K entrepreneurs—In this episode, we cover:(00:00) What open-weight models are and why GLM 5.2 is worth testing(01:38) GLM 5.2 model overview(04:02) Capabilities and benchmark results(06:02) How to set up GLM 5.2 in Cursor(08:37) How to set up GLM 5.2 in Claude Code(11:04) Live test 1: codebase exploration and architecture audit on ChatPRD(12:43) Live test 2: generating an HTML architecture and roadmap page(16:37) Live test 3: redesigning the How I AI landing page in Cursor(20:57) Live test 4: 45-minute autonomous task, pulling Sentry errors and Vercel logs(22:35) Where it struggled(23:49) My verdict on the output(25:23) Cost breakdown—Tools referenced:z.ai: https://z.aiGLM 5.2: https://z.ai/blog/glm-5.2OpenRouter: https://openrouter.aiCursor: https://cursor.comClaude Code: https://docs.anthropic.com/en/docs/claude-codeSentry: https://sentry.ioVercel: https://vercel.com—Other references:SWE-Bench Pro leaderboard (coding benchmark scores referenced in episode): https://www.swebench.comFrontier Suite and Post-Train Bench (additional benchmarks cited): https://scale.com/leaderboardUse Claude Code with OpenRouter: https://openrouter.ai/docs/cookbook/coding-agents/claude-code-integration—Where to find Claire Vo:ChatPRD: https://www.chatprd.ai/Website: https://clairevo.com/LinkedIn: https://www.linkedin.com/in/clairevo/X: https://x.com/clairevo—Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].