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...

MCJudgeBench — leaderboard

Metric: CJAR (self-reported). Source: benchmarklist.com. 7 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)85.8
2Gemini 2.5 Flash Lite85.5
3Qwen 3.5 4B85.3
4Claude Haiku 4.584.8
5Claude Sonnet 4.682.8
6GPT-5.280.9
7Llama 3.2 3B Instruct77

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