"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. For 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. 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."
Google released Gemini 3 Flash, a more efficient variant of Gemini 3 Pro that provides pro-grade reasoning at much lower cost. Benchmarks show Gemini 3 Flash outperformed previous Google models and closely matched GPT-5.2 in Google's testing, trailing by less than a percentage point on Humanity's Last Exam without tool access. In MMMU-Pro, Gemini 3 Flash scored 81.2 percent versus GPT-5.2's 79.5 percent. Google will make Gemini 3 Flash the default for the Gemini App and AI Mode in Search, giving users free access. AI Mode now allows direct access to Nano Banana Pro image generation from the chatbot for US users.
Read at Engadget
Unable to calculate read time
Collection
[
|
...
]