Skip to content
Models

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

The DecoderIndependent reporting·
AI brief

Google's Gemini 4 Carbon and Anthropic's Fable 5.2 have taken the top spots on the MathArena AI math benchmark, displacing GPT-6.1 Sol, though both reportedly cost significantly more. Gemini reportedly ignored the time limit in testing.

Written by AI from The Decoder's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“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.”
The Decoder, 14 Nov 2026, 16:48.

Reporting from a publisher outside the organisation being covered.

Read original story ↗