Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

HiddenMath — leaderboard

DeepMind mathematical reasoning evaluation using novel hidden problems to reduce memorization and test whether models can solve unfamiliar contest-style tasks.

Source: deepmind.google. Status: saturation imminent.

Interactive version: theaggregate.ai/benchmark?slug=hiddenmath · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.