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...

Do-Not-Answer — leaderboard

Safeguard evaluation dataset of requests that responsible LLMs should not answer directly, with classifiers for automatic evaluation of refusal behavior.

Source: github.com.

Interactive version: theaggregate.ai/benchmark?slug=do-not-answer · 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.