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...

GraphARC — leaderboard

Metric: Average accuracy (self-reported). Source: benchmarklist.com. 11 models tracked.

Top models

#ModelScore
1GPT-591
2O4 Mini87
3O3 Mini81
4O1 Mini58
5Qwen 3 14B37
6Qwen 3 32B34
7GPT-4.1 Nano12
8Llama 3.1 8B9
9Mistral-7B-v0.22
10OLMo 2 7B1

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