Google's Gemini 3 Flash model outperforms GPT-5.2 in some benchmarks
Almost exactly a month after the debut of Gemini 3 Pro in November, Google has begun rolling out the more efficient Flash version of its latest AI model. According to the company, the new system offers similar "pro-grade" reasoning performance as its flagship model at a fraction of the cost, making it ideal for everyday use. In benchmarks, the new system performed significantly better than Google's previous generation models, including Gemini 2.5 Pro. More notably, in Google’s testing it managed to trade blows with GPT-5.2, the model OpenAI rushed out to counter Gemini 3 Pro. A table comparing Gemini 3 Flash's performance across a variety of AI benchmarks. GoogleFor example, in the tough Humanity's Last Exam suite, Gemini 3 Flash scored less than a percentage point worse than GPT-5.2 when neither model had access to tools like web search. In a handful of other benchmarks, Google's more efficient system even managed to outperform OpenAI's latest. For instance, in MMMU-Pro, a benchmark designed to test a model's multimodal understanding and reasoning, it edged out GPT-5.2 with a result of 81.2 percent compared to 79.5 percent. Of course, benchmarks only tell a partial story; we'll have to see what people think once both systems are broadly available. Still, the fact Gemini 3 Flash is even close to GPT-5.2, and the "Extra High" reasoning mode at that, is a worrying sign for OpenAI. As with Gemini 3 Pro, Google is rolling out the new model to both the Gemini App and AI Mode in Search where it will be the default model for both services. "That means all of our Gemini users globally will get access to the Gemini 3 experience at no cost, giving their everyday tasks a major upgrade," Google explains. While on the subject of AI Mode, it's now possible to access Nano Banana Pro, Google's latest image generator, directly from the chatbot. Provided you live in the US, select "Thinking with 3 Pro," followed by "Create Images Pro" from the model picker. This article originally appeared on Engadget at https://www.engadget.com/ai/googles-gemini-3-flash-model-outperforms-gpt-52-in-some-benchmarks-160000000.html?src=rss
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
Scale AI launches Voice Showdown, the first real-world benchmark for voice
<p>Voice AI is moving faster than the tools we use to measure it. Every major AI lab — OpenAI, Google DeepMind, Anthropic, xAI — is racing to ship voice models capable of natural, real-time [...]