Kimi K3 Wins in Arcade Game Generation Test
OfirPress · x · 2026-07-17
A hands-on comparison reveals that Kimi K3 performed the best on a task to create three retro arcade games, while also costing less.
Comparison data:
- Kimi K3: 18.4K tokens, $0.28
- GPT-5.6: 18.1K tokens, $0.28
- Opus 4.8: 21.3K tokens, $0.54
The tester noted that the Qbert game built by Kimi K3 was the best of the three. Its Battle City was also the closest to the original, with correct logic for tank movement, aiming, shooting, and wall destruction. While GPT-5.6 had the best visual style, it failed in Battle City, with broken tank and base logic.
Related event: Kimi K3 Tops Frontend Code Arena and Sparks Debate(53 posts)→
More from Models
- Poolside releases Laguna S 2.1, a 118B coding-agent model with 1M context — burny_tech · 2026-07-22
- NVIDIA's Ultra Model Handles Massive Codebases and Long Tool Chains — MonaJalal_ · 2026-07-22
- DeepSeek post pairs inference-system optimizations with a 545% theoretical margin analysis — teortaxesTex · 2026-07-22
- Starcloud pitch puts data centers in space back on the AI infrastructure map — ycombinator · 2026-07-22
- Kimi K3’s only real drawback is speed, but the model is otherwise excellent — bindureddy · 2026-07-22
- Teknium says Anthropic still leads on long-context coherence and cost — Teknium · 2026-07-22