News

Gemini 2.5 Achieves Top Score on MathArena USAMO Evaluation

April 02, 2025
Gemini 2.5 MathArena USAMO Large Language Models Mathematical Olympiad AI Performance
Gemini 2.5 scored 24.4% on the MathArena USAMO evaluation, showcasing its advanced reasoning and generalization capabilities in solving complex mathematical problems.

Gemini 2.5 Achieves Top Score on MathArena USAMO Evaluation

Gemini 2.5 achieved a score of 24.4% on the MathArena USAMO (United States of America Mathematical Olympiad) evaluation, surpassing previous top-performing models. This score reflects its advanced reasoning and generalization capabilities in solving complex mathematical problems.

MathArena is a rigorous platform designed to evaluate large language models (LLMs) on the latest math competitions and olympiads. It ensures fair assessment by testing models only on competitions that occurred after their release, avoiding contamination from pre-trained data. The platform publishes detailed leaderboards and open-sources its evaluation code to maintain transparency and comparability of model performances.

For more details, visit the MathArena website or the discussion on Hacker News.

Sources

Gemini 2.5 gets 24.4% on MathArena USAMO beating previous top ... Gemini 2.5 gets 24.4% on MathArena USAMO beating previous top score of 4.7% Hacker News. This does look like a large relative increase in score ...
MathArena By performing standardized evaluation we ensure model scores are actually comparable and are not dependent on the specific evaluation setup of the model ...
Google's Gemini 2.5 Shocks the World: Crushing AI Benchmark Like ... Math and Science Tests: With strong results on challenges like GPQA and AIME 2025, the model shows it can handle the toughest quantitative and ...