Google introduced Gemini 2.5, its latest experimental artificial intelligence model; it ranked second in a competitive leaderboard for AI-driven web development tools.
On March 25, Google announced that it will allow developers to try out Gemini 2.5 Pro. The company described it as a thinking model, capable of reasoning through thoughts before responding.
Google said this improves both accuracy and performance, particularly in coding, science and math tasks. It said Gemini 2.5 can support more context-aware agents.
Citing self-reported data compiled by the AI benchmarking platform LMArena, Google shared that the new AI model topped the charts in reasoning and knowledge, science and mathematics. Google described Gemini 2.5 as its “most intelligent AI model.”
Google’s new model ranks second in web dev leaderboard
Google’s new AI model ranked second in LMArena’s WebDev leaderboard, a real-time AI coding competition where models compete in web development challenges created by the AI benchmarking