Gemini 3.7 Flash Review: Google's Cheap Model Isn’t Dumb Anymore
60-second summary
Google's budget tier Gemini 3.7 Flash model has successfully produced a playable game, a significant improvement from its earlier release that failed to generate a working file. However, it still lacks reasoning capabilities, and a free 27 billion parameter model outperforms it in writing tasks, highlighting the model's limitations and the value of its more expensive counterparts.
Three weeks after a Flash release that couldn't produce a working file, Google's budget tier zero-shots a playable game. It still can't reason, and a free 27B model still writes better.