Loading...
Help others discover this article by sharing it
Check out more articles from the artificial intelligence category
DeepSeek is set to release a new AI model focused on coding in February, aiming to enhance developer...
Google today released its fast and cheap Gemini 3 Flash model, based on the Gemini 3 released last month, looking to steal OpenAI’s thunder. The company is also making this the default model in the Gemini app and AI mode in search.
The new Flash model arrives six months after Google announced the Gemini 2.5 Flash model, offering significant improvements. On the benchmark, the Gemini 3 Flash model outperforms its predecessor by a significant margin and matches the performance of other frontier models, like Gemini 3 Pro and GPT 5.2, in some measures.
For instance, it scored 33.7% without tool use on Humanity’s Last Exam benchmark, which is designed to test expertise across different domains. In comparison, Gemini 3 Pro scored 37.5%, Gemini 2.5 Flash scored 11%, and the newly released GPT-5.2 scored 34.5%.
On the multimodality and reasoning benchmark MMMU-Pro, the new model outscored all competitors with an 81.2% score.
Google is making Gemini 3 Flash the default model in the Gemini app globally, replacing Gemini 2.5 Flash. Users can still choose the Pro model from the model picker for math and coding questions.
The company says the new model is good at identifying multimodal content and giving you an answer based on that. For instance, you can upload your pickleball short video and ask for tips; you can try drawing a sketch and have the model guess what you are drawing; or you can upload an audio recording to get analysis or generate a quiz.
The company also said the model better understands the intent of users’ queries and can generate more visual answers with elements like images and tables.
Google noted that companies like JetBrains, Figma, Cursor, Harvey, and Latitude are already using the Gemini 3 Flash model, which is available through Vertex AI and Gemini Enterprise.
For developers, the company is making the model available in a preview model through the API and in Antigravity, Google’s new coding tool released last month.
The company said the Gemini 3 Pro scores 78% on the SWE-bench verified coding benchmark, only outperformed by GPT-5.2. It added that the model is ideal for video analysis, data extraction, and visual Q&A, and because of its speed, it is suited for quick and repeatable workflows.
Perplexity CEO Aravind Srinivas says on-device AI represents the biggest threat to traditional data...
OpenAI is reportedly preparing powerful audio AI upgrades for its first ChatGPT hardware, promising...
