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 - Putnam 2025 — leaderboard

Metric: Accuracy (%). Source: matharena.ai. 6 models tracked.

Top models

#ModelScore
1Human Expert100
2GPT-5 Pro77.5
3Gemini 3 Pro (Preview)75.83
4DeepSeek V3.2 Speciale59.17
5GPT-5.1 (High)48.33
6Median Human0

Interactive version: theaggregate.ai/benchmark?slug=matharena-putnam-2025 · 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.