Muse Spark 1.1 generated 3D arcade games for $0.026, versus $0.073 for Gemini 3.6
rohanpaul_ai · x · 2026-07-23
An experiment from Atomic Chat compares two models on generating self-playing 3D tabletop arcade games.
Muse Spark 1.1 completed three tasks — 8-ball pool, air hockey, and foosball — for $0.026 using 31.3K tokens. Gemini 3.6 Flash used fewer tokens at 28.8K, but cost $0.073 and produced weaker outputs, with glitches and poorer rendering. The post argues that real-time physics and game logic make these tasks genuinely hard.
Related event: Atomic Chat Goes Open Source and Generates 3D Games at Minimal Cost(2 posts)→
More from Models
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11