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...

OpenEvals - EvasionBench — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 5 models tracked.

Top models

#ModelScore
1GLM-4.782.91
2Qwen 3 Coder 480B A35B Instruct78.16
3MiniMax-M2.171.31
4DeepSeek V3.266.88
5Kimi K2 090566.68

Interactive version: theaggregate.ai/benchmark?slug=openevals-evasionbench · 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.