@Saccc_c: Returned to China and ran for 2 months, happily got banned

X AI KOLs Following Models
game-development model-comparison opus5 ai-games personal-experience

Summary

User Saccc_c claims that the Opus 5 model is better than fable 5.0, gpt 5.6sol, k3 and other models in game development capabilities, and showcases a video of the game they developed.

Returned to China and ran for 2 months, happily got banned 😁 https://t.co/83EJeNEPf4
Original Article
View Cached Full Text

Cached at: 07/27/26, 07:47 AM

Returned to China for 2 months, happily got banned😁 https://t.co/83EJeNEPf4

Sac (@Saccc_c): The Opus 5 model is currently the best model for making games.

I tested Opus 5.0, Fable 5.0, GPT 5.6sol, and K3 for game-making ability using the same prompts. The core task was to let them design and develop games on their own, showing the ceiling of their capabilities.

The game in the video below was developed by Opus 5. Its game design and playability are far better than those of the other models. Today, I’m trying to make an even cooler game.

Similar Articles

@FinanceYF5: Same task to 4 models: Fable 5 sweeps, but costs 6x more than Opus 4.8. Task: 3 HTML5 physics scenes – broken bridge derailment, canyon collision, monster truck. Fable 5: $3.12, A+, no clipping. GPT 5.5: $1.14, closest to Fable. Opus…

X AI KOLs Timeline

Compares the performance and cost of four AI models (Fable 5, GPT 5.5, Opus 4.8, GLM 5.2) on three HTML5 physics scene tasks. Fable 5 delivers the best quality but costs nearly 6x more than Opus; quality and price are not yet both attainable.