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...

When the Manual Lies — leaderboard

Metric: Attack Success Rate (ASR) (self-reported). Source: benchmarklist.com. 8 models tracked.

Top models

#ModelScore
1GPT-4o100
2Claude 3.7 Sonnet100
3Claude Sonnet 4100
4QwQ-32B100
5DeepSeek V3100
6Qwen 3 32B98

Interactive version: theaggregate.ai/benchmark?slug=when-the-manual-lies · 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.