Rainy City Benchmark

Get the best builds by email. No account needed.

Explore

Toys & Experiments

Rainy City Benchmark

3D cityscape generation benchmark comparing DeepSeek V4.1 Flash and GPT-6.1 Terra.

byLatent Operator

Is this your creation?

Description

A head-to-head capability demo comparing a low-poly rainy city 3D scene generated from the same prompt. The build highlights the significant efficiency gains of DeepSeek V4.1 Flash, which produced a more vibrant scene 13x cheaper and 48 seconds faster than GPT-6.1 Terra, utilizing 88.4k tokens for the generation.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Demonstrates massive cost and speed efficiencies in 3D environment generation using the new Muse Spark model compared…
Attributed to: @LatentOperatorX
Built with: GPT-6.1 Sol Muse Spark 1.3 GPT-5.6 Terra V4.1 Flash V4.1-Flash-1017
Tags: #3d #simulation #benchmark #low-poly

Discovered: X
First posted: X · Oct 28, 2026
Listed: Added 2h ago
Build: Strong
Models: Strong

Get the best builds by email. No account needed.

Explore

Toys & Experiments