arXivBo Zou, Chao XuMon, May 25, 2026, 8:29 AM PDT
score 16.4
New benchmark measures how creatively LLMs can write stories
Original: QUIET: A Multi-Blank Cascaded Story Cloze Benchmark for LLM Creative Generation Capability
Source: arxiv.org ↗
Writing ELI5 summary…