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...

When Reviews Disagree — leaderboard

Metric: ρ (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)45.23
2GPT-5.236.79
3Llama 3 8B Instruct35.41
4Llama 4 Maverick33.15
5Qwen 2.5 7B Instruct28.54

Interactive version: theaggregate.ai/benchmark?slug=when-reviews-disagree · 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.