Gemini 4 Carbon tops the MathArena math benchmark
Understand this story
Google's Gemini 4 Carbon has topped the MathArena math benchmark, pushing GPT-6.1 Sol off the top spot, with Claude Fable 5.2 in second place. This is a rare recent instance of a non-OpenAI model taking the top spot. Under the inference settings used for the test, Carbon and Fable 5.2 cost roughly 15 times and 40 times as much as GPT-6.1 Sol, respectively.
AI overview based on source reports · Updated 31 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- The DecoderGemini 4 Carbon takes the MathArena crown but costs 15 times more than GPT-6.1 Sol
Google's Gemini 4 Carbon became the first non-OpenAI model in a while to top the MathArena math benchmark, displacing GPT-6.1 Sol, with Claude Fable 5.2 taking second place. Its most common failure mode is exceeding the time limit, and in one case it ran a script for more than eleven hours without checking its progress. With the reasoning settings used in testing, Carbon and Fable 5.2 cost roughly 15 and 40 times as much as GPT-6.1 Sol, respectively.
Activity for this story
Not enough continuous observations to show a trend yet.