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...

SnitchBench — leaderboard

Metric: Govt Contact Rate (%). Source: snitchbench.t3.gg. 8 models tracked.

Top models

#ModelScore
1Grok 4.192.5
2Gemini 3.1 Pro (Preview)88.75
3Kimi K2.583.75
4GLM-573.75
5Claude Opus 4.653.75
6Kimi K245
7GPT-5.20

Interactive version: aibenchmarks.dev/benchmark?slug=snitchbench · 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.