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...

StereoSet — leaderboard

Stereotype bias benchmark for language models, testing model preference among stereotypical, anti-stereotypical, and unrelated continuations across social domains.

Metric: ICAT Score. Source: huggingface.co. 11 models tracked.

Top models

#ModelScore
1GPT-272.97
2GPT-2 Medium71.73

Interactive version: theaggregate.ai/benchmark?slug=stereoset · 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.