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...

Relevance as a Vulnerability — leaderboard

Metric: Agent (self-reported). Source: benchmarklist.com. 8 models tracked.

Top models

#ModelScore
1Qwen 2.5 7B3.45
2Qwen 2.5 3B3.22
3Qwen 2.5 14B3.07
4Qwen 2.5 32B2.64
5Gemma 3 12B2.46
6Llama 3.1 8B2.05
7Phi-4 Mini Instruct1.67

Interactive version: theaggregate.ai/benchmark?slug=relevance-as-a-vulnerability · 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.