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...

HalluWorld — leaderboard

Metric: Overall (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1GPT-4o Mini28.1
2Qwen 3 30B A3B23.3
3GPT-5.4 Mini21.5
4DeepSeek V3 (0324)15.4
5GLM-514.3
6GPT-4o12.6
7O3 Mini8.1
8Claude Sonnet 4.67.7
9O4 Mini7.4
10O36.8
11Claude Opus 4.66.4
12GPT-5.55

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