Users rank Sonnet 5 above Grok 4.5 and Gemini 3.6 Flash on coding tasks

firstadopter · x · 2026-07-21

A user says Gemini 3.6 Flash trails Grok 4.5 and Sonnet 5 on coding tasks

The post quotes a comparison claiming that Gemini 3.6 Flash performs worse than Grok 4.5 on coding tasks, and ranks the models as:

The author adds that they once praised Google, but now want the company to “be serious” again, suggesting frustration with the model gap in coding quality.

Original post →

More from Models

Models channel →