ModelsBig techResearch

Gemini 4 Carbon takes the MathArena crown but costs 15 times more than GPT-6.1 Sol

via The Decoder · 34 views · 1w ago

OpenAI just lost its math crown. 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 now taken the top spots, knocking GPT-6.1 Sol from the lead. This is a significant shake-up in AI math capabilities, highlighting intense competition among big tech players. However, this advancement comes at a price. Gemini 4 Carbon costs a staggering 15 times more than GPT-6.1 Sol. So, while AI is getting smarter at math, expect to pay a premium for that cutting-edge performance.

Read the original story →

← Back to the feed

Loading comments…

Log in to join the conversation.