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…
- Modality
- text
- Categories
- reasoning
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 2
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.01 | 2025-08-07 | evidence |
| Grok-4.1 | xAI | 0.9703 | 2025-11-17 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.