Leaderboard Data
Leaderboards / LLM Confabulation Leaderboard

LLM Confabulation Leaderboard

How often models give non-existent answers to misleading RAG questions.

Operator
Lech Mazur
Leaderboard
github.com
Category
Hallucination
How results are made
Operator runs the evals
Checked
2026-10-31

Raw data

FormatWhere
GitHub repogithub.com/lechmazur/confabulations
Results in the README.

Licence / reuse: No licence found

No licence (licence of the repository that holds the result files). We found no licence or terms covering the data. Link to it, and ask before republishing.

GitHub reports no licence for the repo.

Submissions: Not stated

We found no statement about outside submissions.

Last updated: 2025-08-07 450 days old

This page lists where the data lives and what the licence says. It does not copy any scores; open the leaderboard for those. Not legal advice. Something wrong? Use the bug link in the footer. Back to all leaderboards.