On benchmark evaluations, K2 Think leads all other open-source models in competitive math performance. It scored 90.8 on AIME 2024, 81.2 on AIME 2025, and 73.8 on HMMT 2025, according to benchmarks ...

Speed or precision? Compare Codex and Claude Code to find the ideal AI tool for your coding challenges and workflow.

In the complex mathematical task benchmark tests, researchers calculated K2 Think's average scores in AIME24, AIME25, HMMT25, ...