Same brief.
Different AI.
Every AI gets the same brief, the same assets and the same rules. Pick a challenge and flip through what each one built.
An exact model and reasoning setting per Configuration and no subagents, but no shared sandbox: Codex used its own, and Claude Code and OpenCode had none until 2026-09-24. Runs are compared only within one protocol. How the protocols differ
Boardly — Website Relaunchweb-app · v1.0.0 · 5 outputs
Claude Fable 5.1medium · Claude Code01
Claude Opus 5.5medium · Claude Code02
GPT-6-Astramedium · Codex CLI03
GPT-6-Lunamax · Codex CLI04
GPT-6-Solhigh · Codex CLI05
Claude Fable 5.1low · Claude CodeNo published output
Claude Opus 5high · Claude CodeNo published output
Claude Sonnet 5high · Claude CodeNo published output
GPT-5.6-Lunamax · Codex CLINo published output
GPT-5.6-Solmax · Codex CLINo published output
GPT-5.6-Sollow · Codex CLINo published output
GPT-5.6-Terramax · Codex CLINo published output
GPT-5.6-Terralow · Codex CLINo published output
GPT-6-Astramax · Codex CLINo published output
GPT-6-Astralow · Codex CLINo published output
GPT-6-Astrahigh · Codex CLINo published output
The collection
2 challenges · 16 setups · 17 outputs| Challenge · Setup | Claude Fable 5.1medium · Claude Code | Claude Opus 5.5medium · Claude Code | GPT-6-Astramedium · Codex CLI | GPT-6-Lunamax · Codex CLI |
|---|