Recreating 1994's Theme Park: Claude Opus 5.5 clearly beats GPT-6.1 Sol at game building
rschu · x · 2026-10-02
Inspired by the 1994 Amiga classic Theme Park (co-designed by DeepMind's Demis Hassabis), the author cloned it as "Scheme Park" and benchmarked frontier models: GPT-6.1 Sol with OpenAI's official Codex Game Studio plugin produced poor results, and GPT-6 Astra with more compute wasn't much better. Claude Opus 5.5 clearly won with a playable clone, better graphics and synth tunes. The Opus workflow took 3 iterations — idea sharing, scoping a v1 spec, then a one-shot prompt that worked perfectly on the first try. Demo videos included.
Related event: Theme Park Remake Pits GPT-6.1 Sol Against Claude Opus 5.5(2 posts)→
More from coding & agent
- Make AI agents parallelize work — 5x-10x speedups by telling them to use your machine's cores — Daniel_Farinax · 2026-10-02
- BIABench: No AI agent scores above 0.19 on 3D bioimage analysis tasks — notredame · 2026-10-02
- 24 procedural animals generated entirely in code with Opus 5.5 — SDF sculpting, rigging, fur, IK, all runtime — majidmanzarpour · 2026-10-02
- Agents talking too much? Let them return generative UI instead, says A2UI framing — rseroter · 2026-10-02
- Dev open-sources all five Claude Code skills behind his Sudoku project — SeanOliver · 2026-10-02
- Dev shares a Claude Code docs skill that keeps README and agent instructions in sync with code — SeanOliver · 2026-10-02