Gemini 3.7 Flash Performance Drops Below Gemma Due to OpenRouter Backend Variances

mariofilhoml · x · 2026-08-14

The author found that the newer Gemini 3.7 Flash performed worse than Gemma on a structured text extraction task. Upon investigation, they discovered that when using Gemini models via OpenRouter for structured output, the underlying backend (Vertex vs. AI Studio) causes wildly different performance.

This serves as a warning for developers to account for backend discrepancies when running model evaluations.

Related event: Gemini 3.7 Flash Structured Output Varies by Backend(2 posts)→

Original post →

More from Models

Models channel →