Gemini 4 Carbon tops MathArena at 15x GPT-6.1 Sol's cost
Start here
Google's Gemini 4 Carbon has topped the MathArena math benchmark, displacing GPT-6.1 Sol and becoming the first non-OpenAI model in a while to hold the top spot, according to The Decoder. Anthropic's Claude Fable 5.2 placed second. The report lists expected scores of 85.4% for Gemini 4 Carbon, 82.8% for Claude Fable 5.2 and 80.6% for GPT-6.1 Sol. Under the reasoning settings used in testing, Gemini 4 Carbon and Claude Fable 5.2 cost roughly 15 and 40 times as much as GPT-6.1 Sol, respectively. The report also notes that Gemini 4 Carbon's most common failure mode is exceeding the time limit.
Generated from reports · updated 14 min ago
Report timeline
Follow the reports to see the event from different sides.
- The DecoderGemini 4 Carbon tops MathArena but costs 15 times more than GPT-6.1 Sol
Google's Gemini 4 Carbon has become the first non-OpenAI model in a while to top the MathArena math benchmark, displacing GPT-6.1 Sol, with Anthropic's Claude Fable 5.2 taking second place. In the tested reasoning settings, Gemini 4 Carbon and Claude Fable 5.2 cost roughly 15 and 40 times as much as GPT-6.1 Sol, respectively. The report lists expected performance of 85.4% for Gemini 4 Carbon, 82.8% for Claude Fable 5.2 and 80.6% for GPT-6.1 Sol, and notes that Gemini 4 Carbon's most common failure mode is exceeding the time limit.
Heat for this event
Not enough continuous observations yet to draw a trend.