ModelRefs / LongFact Concepts Leaderboard — AI Model Scores
LongFact Concepts Leaderboard — AI Model Scores
Long-form factuality benchmark measuring unsupported claims in open-ended concept answers. Current leaders, methodology, and citation sources for LongFact Concepts.
Overview
Long-form factuality benchmark measuring unsupported claims in open-ended concept answers.
How it is measured: Claim-level hallucination rate using a browsing-enabled model grader; lower is better.
How this benchmark is scored
| Category | reasoning |
|---|---|
| Maximum score | 100 % hallucination rate |
| Direction | Lower is better |
Primary source: https://arxiv.org/abs/2403.18802
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to LongFact Concepts Leaderboard — AI Model Scores.