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...

PM-AGI - Difficulty - Hard — leaderboard

Metric: Score (%). Source: huggingface.co. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.798.4
2GPT-5.297.2
3GPT-5.496.9
4Gemini 2.5 Flash89.8
5Gemini 3 Flash (Preview)89.3
6Gemini 2.5 Pro84.3
7GPT-5.573

Interactive version: theaggregate.ai/benchmark?slug=pm-agi-difficulty-hard · 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.