Duly Noted

Flash 3 with thinking disabled is smarter, faster, and cheaper than its closest competition Haiku 4.5, and while it’s not quite as smart as GPT-5 mini (with default reasoning), it’s about the same price and 8x faster. Meanwhile, GPT-5 mini gives up significantly more intelligence with reasoning dialed back to minimal (the lowest 5 mini can go).

I dunno. I feel like I get better results with thinking models. But what do I know. I couldn’t empirically defend that.

_{Quote Citation: Brokk, “Why Gemini 3 Flash is the model OpenAI is afraid of”, 2025-12-18, https://blog.brokk.ai/why-gemini-3-flash-is-the-model-openai-is-afraid-of/}