Benchmark
LongFact Concepts
LongFact is a benchmark for evaluating long-form factuality in large language models. It comprises 2,280 fact-seeking prompts spanning 38 topics, designed…
- Modality
- text
- Categories
- reasoning, general
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.007 | 2025-08-07 | 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.