One prompt
One-prompt builds. Same prompt, no picture, one run each.
Each model gets the same frozen prompt and no picture, and builds it in one run with no human edits. Every build is served exactly as the agent wrote it, for you to open in your browser.
These are not CmdBench benchmark runs: no checks, scores or verdicts.
-
-
GPT-6.2 Sol, low -
GPT-6.2 Sol, medium -
GPT-6.2 Sol, high -
GPT-6.2 Sol, xhigh -
GPT-6.2 Astra, low -
GPT-6.2 Astra, medium -
GPT-6.2 Astra, high -
GPT-6.2 Astra, xhigh
Voxel sandbox game, GPT-6.2
OpenAI's GPT-6.2 Sol and GPT-6.2 Astra, released on 17.11.2026, each built a first-person voxel sandbox game in Codex CLI from the same prompt and no picture: a generated block world to walk through, mine and build in. One run each on low, medium, high and xhigh effort, with no human edits.
-
-
-
Claude Fable 5.2 -
Claude Opus 5.5 -
GPT-6.1 Sol
Voxel sandbox game
Claude Fable 5.2 and Claude Opus 5.5 in Claude Code and GPT-6.1 Sol in Codex CLI each built a first-person voxel sandbox game from the same prompt and no picture: a generated block world to walk through, mine and build in. One run each on high effort, with no human edits.
-
-
-
Claude Fable 5.2 -
Claude Opus 5.5
Paper boat short film
Claude Fable 5.2 and Claude Opus 5.5 in Claude Code each made a 30-second animated film from the same prompt and no picture: a paper boat in a night storm, found by a lighthouse beam and guided into a calm harbour at sunrise. One run each on high effort, with no human edits.
-