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...

BlueBench - Reasoning — leaderboard

Metric: Score (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1O179
2GPT-4o78
3GPT-4.177.5
4O4 Mini75.5
5Mistral Medium 375.5
6Mistral Large75
7Llama 3.3 70B Instruct73.5
8Pixtral-12B73.5
9GPT-4.1 Mini73
10O3 Mini73
11GPT-4.1 Nano69
12Llama 3.2 3B Instruct56
13Llama 3.2 1B Instruct41

Interactive version: theaggregate.ai/benchmark?slug=bluebench-reasoning · 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.