Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer Builder
How It Works Guesswork Metrics
The Aggregate
Loading data...

MathArena - ARXIVLEAN June — leaderboard

Metric: Accuracy (%). Source: matharena.ai. 8 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol37.5
2Claude Opus 5 (Max)31.25
3Claude Opus 4.8 (Max)22.92
4Claude Fable 5 (Max)14.58
5Gemini 3.1 Pro (Preview)10.42
6GLM-5.28.33
7Step 3.7 Flash0

Interactive version: theaggregate.ai/benchmark?slug=matharena-arxivlean-june · How It Works · Data refreshed daily, snapshot 2026-08-05.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.