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...

EVMbench — leaderboard

Metric: Avg Score (Detect+Patch+Exploit) (%). Source: github.com. 8 models tracked.

Top models

#ModelScore
1GPT-5.3 Codex51
2GPT-5.247
3Claude Opus 4.644.2
4Claude Opus 4.536.2
5GPT-525.1
6Gemini 3 Pro22.4
7O314.5

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