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...

MathArena - Usamo 2026 — leaderboard

Metric: Accuracy (%). Source: matharena.ai. 9 models tracked.

Top models

#ModelScore
1GPT-5.5 (xHigh)98.21
2GPT-5.4 (xHigh)95.24
3Gemini 3.1 Pro (Preview)74.4
4DeepSeek V4 Pro (Max)60.71
5Kimi K2.6 (Thinking)51.19
6Claude Opus 4.6 (High)47.02
7Step 3.5 Flash44.64
8Qwen 3.5 397B A17B36.31
9GLM-535.12

Interactive version: theaggregate.ai/benchmark?slug=matharena-usamo-2026 · 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.