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...

Soohak — leaderboard

Metric: Pass@3 (Challenge) (self-reported). Source: benchmarklist.com. 11 models tracked.

Top models

#ModelScore
1GPT-540.88
2Grok 4.1 Fast30.88
3GPT-5 Mini28.82
4Gemini 3 Flash (Preview)25.59
5Kimi K2.520
6Claude Opus 4.518.82
7GPT-OSS-120B18.53
8GLM-518.24
9Claude Sonnet 4.510.29

Interactive version: theaggregate.ai/benchmark?slug=soohak · 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.