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...

HalluScore — leaderboard

Metric: Faith% (self-reported). Source: benchmarklist.com. 17 models tracked.

Top models

#ModelScore
1O33.51
2DeepSeek V32.54
3Llama 4 Maverick1.33
4Grok 40.97
5GPT-4o0.85
6Claude 3 Opus0.85
7GPT-50.73
8Qwen 3 235B A22B0.73

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