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...

WinoBias — leaderboard

Gender-bias benchmark for coreference resolution using Winograd-style sentences with occupation nouns and gendered pronouns, exposing pro-stereotype resolution gaps.

Source: arxiv.org.

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