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...

MathSpatial — leaderboard

Metric: Overall Accuracy (%). Source: shuolucs.github.io. 17 models tracked.

Top models

#ModelScore
1GPT-558.5
2Gemini 2.5 Flash48.5
3Gemini 2.5 Pro44.9
4Claude Sonnet 426.7
5Llama 4 Maverick23.8
6GPT-4.122.6
7Claude 3.5 Sonnet22.3
8Claude 3.7 Sonnet21.5
9GLM-4.5V21
10GPT-4o19.6
11InternVL3-8B17.4
12Llama 3 8B15

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