Benchmark

SQuALITY

summarization long_context language text

SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a long-document summarization dataset built by hiring highly-qualified contractors to read public-domain short stories (3000-6000 words) and write original summaries from scratch. Each document has five summaries: one overview and four question-focused summaries. Designed to address limitations in existing summarization datasets by providing high-quality, faithful summaries.

语言EN
满分1
参评模型5

模型排名

名次 模型 机构 分数 来源
1 Phi-3.5-mini-instruct Microsoft 24.3 来源 ↗
2 Phi-3.5-MoE-instruct Microsoft 24.1 来源 ↗
3 Nova Pro Amazon 19.8 来源 ↗
4 Nova Lite Amazon 19.2 来源 ↗
5 Nova Micro Amazon 18.8 来源 ↗