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...

EVALITA - MAIA-MC — leaderboard

Metric: CPS. Source: huggingface.co. 7 models tracked.

Top models

#ModelScore
1Qwen 2.5 VL 32B Instruct87.26
2Qwen 2.5 VL 7B Instruct81.77
3Gemma 3 27B (IT)81.43
4Pixtral-12B80.27
5aya-vision-8B75.88
6Gemma 3 4B (IT)69.32
7GLM-4.1V-9B (Thinking)59.61

Interactive version: theaggregate.ai/benchmark?slug=evalita-maia-mc · 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.