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...

MME-CC — leaderboard

Metric: Overall Score (%). Source: randomtutu.github.io. 16 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro42.66
2GPT-5 (High)40.25
3Gemini 2.5 Flash37.57
4O4 Mini (High)35
5GPT-4.132.14
6GLM-4.5V30.45
7GLM-4.1V-9B (Thinking)19.3
8Qwen 2.5 VL 32B Instruct14.39
9InternVL3-8B11.36
10Qwen 2.5 VL 7B Instruct7.5

Interactive version: theaggregate.ai/benchmark?slug=mme-cc · 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.