Lawson had a coding agent build one Pokémon app, using the PokéAPI, in twelve frameworks and meta-frameworks. He ran Opus 5.5 at high effort through Claude Code in a sandbox, five times per framework, and reports medians against a…
In the News: November 1, 2026 (Morning)
A 12-framework benchmark prices one agent-built app from $2.67 to $4.97 a run, and OpenAI will pool ChatGPT and Codex usage in December.
Morning edition
Machine-readable
Download Markdown
Story
Building the same app with Claude Code costs $2.67 to $4.97 depending on the framework
Read story →
Story
OpenAI will share one usage allowance between ChatGPT and Codex from December
OpenAI's help page says that starting in December, the Plus, Pro and Business plans' usage allowance "will be shared across ChatGPT and Codex." Usage will be measured in tokens, and how much of the allowance a request uses depends on the…