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...

CFMME — leaderboard

Metric: Average (self-reported). Source: benchmarklist.com. 16 models tracked.

Top models

#ModelScore
1Qwen 3 VL 235B A22B (Thinking)66.11
2Qwen 3 VL 235B A22B Instruct63.31
3GLM-4.5V60.78
4Qwen 3 VL 8B (Thinking)53.85
5Qwen 3 VL 8B Instruct52.83
6GLM-4.1V-9B (Thinking)51.51
7GPT-4o46.96
8Llama 3.2 11B Vision Instruct20.2

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