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 Accuracy — leaderboard

Metric: Accuracy (%). Source: github.com. 7 models tracked.

Top models

#ModelScore
1GPT-4o44.44
2Claude Opus 4.738.78
3Gemma 4 31B (IT)35.88
4Llama 3.3 70B Instruct31.82
5GPT-4o Mini30.3
6GPT-5 (Medium)28.79
7DeepSeek V3.127.27

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