Benchmark
LongFact Objects Benchmark
What is LongFact Objects?
LongFact is a benchmark for evaluating long-form factuality in large language models. It comprises 2,280 fact-seeking prompts spanning 38 topics, designed to…
- Modality
- text
- Evaluates
- reasoning, general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
LongFact Objects results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.008 | 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.