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...

From Knowing to Doing — leaderboard

Metric: Total ret. (self-reported). Source: benchmarklist.com. 10 models tracked.

Top models

#ModelScore
1Qwen 3.6 Plus85.29
2GPT-5.561.26
3Claude Opus 4.758.8
4MiniMax-M2.756.31
5Step 3.5 Flash21.86
6Gemini 3.1 Pro (Preview)8.25
7DeepSeek V4 Pro1.39
8GLM-5.1-3.55

Interactive version: theaggregate.ai/benchmark?slug=from-knowing-to-doing · 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.