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...

RAG Hallucination Leaderboard (lechmazur) — leaderboard

Measures how frequently LLMs hallucinate when using Retrieval-Augmented Generation. Deliberately challenging. Ranks 70+ models by confabulation rate and non-response rate with adjustable weighting.

Source: lechmazur.github.io. Status: saturated.

Interactive version: theaggregate.ai/benchmark?slug=rag-hallucination-leaderboard-lechmazur · 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.