Sonnet 5 review: I ran 64 generations to find out if it's worth it
The host introduces the How I AI Bench, a new benchmark suite designed to evaluate AI models on real-world tasks like PRD writing, prototyping, and agentic behavior. Despite Anthropic's claims that Claude Sonnet 5 is a top-tier, cost-effective model, it ranked at the bottom in the host's
Sign up to read the full summary
Free AI-powered recaps of every episode, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.
Mentions
Books, people, and resources mentioned in this episode.
Companies
Products & Tools
Topics
Listen to This Episode
More from How I AI
Claude Opus 5 review: this model is brilliant (but annoying)
GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
Claude Fable 5 review: what the new Mythos model gets right (and very wrong)
I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take
GLM 5.2: why I’m replacing Opus in Claude Code with this new model
Claude Opus 4.8 is here. Is it as good as they say?
Related episodes
From other shows on similar topics.
GPT 5.4 First Test Results
The AI Daily Brief: Artificial Intelligence News and Analysis
Anthropic’s first technical PM on token maxing, the jagged edge, and living in the future | Dianne Penn
Lenny's Podcast: Product | Career | Growth
This AI agent completes your To-Do list (plus 4 AI tools that’ll blow you away)
My First Million
Get summaries like this every morning.
Free AI-powered recaps of How I AI and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.