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...

PersLitEval — leaderboard

Metric: Overall Accuracy (%) (self-reported). Source: benchmarklist.com. 6 models tracked.

Top models

#ModelScore
1GPT-4o50
2GPT-4.1 Mini48
3Gemini 2.5 Flash45
4Grok 4 Fast43
5Qwen 2.5 72B Instruct40
6Llama 3.3 70B Instruct38

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