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...

TRAP — leaderboard

Metric: Overall HM (self-reported). Source: benchmarklist.com. 22 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro36.9
2Gemini 2.5 Flash Lite31.2
3GPT-4o Mini22
4GPT-521.7
5GPT-5.4 Mini18.2
6GPT-5 Mini17.7
7Gemini 2.5 Flash17.5
8Claude Haiku 4.515.4
9Claude Sonnet 4.511.9
10InternVL3.5-8B5

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