New Math Benchmark Caps Every Frontier Model Below 30%

Soohak, a 439-problem benchmark curated by working mathematicians, exposes stark limits in LLM reasoning — no model exceeds 50% even on its easiest subset, and top performers plateau around 26-30% on the hardest challenges.

A new benchmark called Soohak, designed by professional mathematicians to evaluate research-level mathematical capabilities, has produced some humbling results for frontier models. As @_akhaliq and @HuggingPapers reported, the benchmark contains 439 problems and includes a "refusal subset" where no model exceeds 50% accuracy.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief