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...

CMMMU (Validation) — leaderboard

Metric: Validation Overall (%). Source: cmmmu-benchmark.github.io. 35 models tracked.

Top models

#ModelScore
1GPT-4o52.2
2flan-t5-xxl36.8
3vicuna-13B35.1
4GPT-432.9
5Llama 2 7B30.7
6Baichuan-7B26
7Yi 6B (Base)25.6
8Qwen-7B24.7

Interactive version: theaggregate.ai/benchmark?slug=cmmmu-validation · 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.