Testing Qwen 3.8 Frontend Capabilities

hqmank · x · 2026-07-19

A developer tested the frontend coding abilities of the newly released Qwen 3.8 model. The task was to rebuild a 3D globe dashboard with a single prompt and one reference image. Results showed the model generated a structurally complete and runnable page, but performed moderately on details like lighting and glass texture; some elements didn't match the reference. Overall frontend capability lags behind top models like Kimi K3.

Original post →

More from Models

Models channel →