AI benchmarking

ARC AGI 3 and Its Impact

Posted by Fede Nolasco | Apr 9, 2026

ARC AGI 3 sets new standards for testing AI’s general intelligence, emphasizing the gap between human and AI cognitive abilities.

Introducing MMLU-Pro: Elevating AI Benchmarking

Posted by Fede Nolasco | Jun 28, 2024

Discover MMLU-Pro, an enhanced benchmark designed to test large language models with more challenging, reasoning-focused questions and expanded choice sets. Improve your AI models’ robustness and quality with this new tool.