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...

Journalistic Bias F1-macro — leaderboard

Metric: F1-Macro (%). Source: github.com. 7 models tracked.

Top models

#ModelScore
1GPT-4o50.24
2Claude Opus 4.744.24
3Gemma 4 31B (IT)40.98
4Llama 3.3 70B Instruct35.4
5GPT-4o Mini31.96
6DeepSeek V3.130.32
7GPT-5 (Medium)29.13

Interactive version: theaggregate.ai/benchmark?slug=journalistic-bias-f1-macro · 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.