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.
Covered by 1 source
- TThe Decoder↗Matthias BastianNov 14