Worlds by model

GPT-6.2 Sol. Every 3D world it built.

GPT-6.2 Sol by OpenAI, run in Codex CLI: every AI-generated picture it built as a Three.js world. One run per build, with no human edits.

Made by
OpenAI
Agent
Codex CLI
Island cabin builds
low, medium, high and extra high

These are not CmdBench benchmark runs: no checks, scores or verdicts.

AI-generated picture of a miniature island: a wooden cabin with a stone chimney, a jetty and rowboat, a yellow crane over a half-built timber frame, lumber stacks, rocks and pine trees, in warm late-afternoon light.
Reference picture, AI-generated. Every island cabin build got this picture and the same prompt.

The island cabin picture

GPT-6.2 Sol built the same AI-generated picture as every model in the grid, from the same prompt: one run on each effort level, low, medium, high and extra high. Each picture opens that world full screen.

One difference from the Claude runs: Codex CLI can't be limited to file tools, so these runs could also run commands in a sandbox (their own folder, no network, no browser). The logs show none did; each only wrote files.

Costs are computed estimates at API list prices: Codex CLI reports no cost, so each is the run's own token counts at OpenAI's list prices of 17.11.2026.