← Back to Model Beat
Models·Nov 14·all news from November 14, 2026

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

Google's Gemini 4 Carbon and Anthropic's Fable 5.2 have surpassed GPT-6.1 Sol to take the lead on the MathArena benchmark. While these new models demonstrate improved performance in complex mathematical tasks, they cost approximately 15 times more than the previous leader. This result marks a shift in the competitive landscape where top-tier accuracy is now linked to significantly higher operational expenses.

ModelsGemini 4 CarbonGPT-6.1 Sol

Covered by 1 source

Related stories

ModelsGemini 4 Carbon is now availableNov 10 · 7 sourcesModelsGemini 4 Carbon: Our next frontier modelOct 28 · 9 sourcesModelsIntroducing GPT-6.1 SolSep 29 · 6 sourcesModelsAsana cuts model costs 76x in browser tests with GPT-6.1 SolOct 9