Gemini 4 Carbon takes the MathArena crown but costs 15 times more than GPT-6.1 Sol
The Decoder
For the first time in a while, no OpenAI model leads the MathArena AI math benchmark. Google's Gemini 4 Carbon and Anthropic's Fable 5.2 have knocked GPT-6.1 Sol from the top, though both cost significantly more.
Summary drawn from The Decoder's own description of the story.