Benchmark

SQuALITY

SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a long-document summarization dataset built by hiring highly-qualified…

Modality
text
Categories
long_context, summarization, language
Openness
unknown
Source
llm_stats
Reported scores
5

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Nova LiteAmazon0.1922024-11-20evidence
Nova MicroAmazon0.1882024-11-20evidence
Nova ProAmazon0.1982024-11-20evidence
Phi-3.5-mini-instructMicrosoft0.2432024-08-23evidence
Phi-3.5-MoE-instructMicrosoft0.2412024-08-23evidence

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.