Benchmark

LongFact

LongFact evaluates factual precision over long-form generations containing many individual claims. Each claim is extracted and verified, and the model is…

Modality
text
Categories
factuality, general
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
MAI-Thinking-1Microsoft0.982026-06-02evidence

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.