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...

MMMLU (Opus 4.6 System Card) — leaderboard

Metric: Accuracy (%). Source: www-cdn.anthropic.com. 5 models tracked.

Top models

#ModelScore
1Gemini 3 Pro91.8
2Claude Opus 4.6 (Thinking)91.1
3Claude Opus 4.5 (Thinking)90.8
4GPT-5.289.6
5Claude Sonnet 4.589.5

Interactive version: theaggregate.ai/benchmark?slug=mmmlu-opus-4-6-system-card · 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.