reasoning benchmark
FActScore
A fine-grained atomic evaluation metric for factual precision in long-form text generation that breaks generated text into atomic facts and computes the percentage supported by reliable knowledge sources, with automated assessment using retrieval and language models
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
FActScore leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | XA | 97.0% | 100.0% | 2 | C | |
| 2 | OP | 1.0% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
FActScore highlights
The top published results on this benchmark's own scale.
What is FActScore?
Definition and scoring fields from the benchmark registry.
A fine-grained atomic evaluation metric for factual precision in long-form text generation that breaks generated text into atomic facts and computes the percentage supported by reliable knowledge sources, with automated assessment using retrieval and language models
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- FActScore
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- factscore|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about FActScore.
Which model scores highest on FActScore?
Grok-4.1 is currently ranked first with 97.0%.
What does FActScore measure?
A fine-grained atomic evaluation metric for factual precision in long-form text generation that breaks generated text into atomic facts and computes the percentage supported by reliable knowledge sources, with automated assessment using retrieval and language models
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.