LongBench v2
arxiv.org ↗(2025) - 503 expert-crafted multiple-choice questions spanning 8K-2M-word contexts with deep multi-hop reasoning; humans score 53.7% under time pressure.
AboutVisit arxiv.org ↗
(2025) - 503 expert-crafted multiple-choice questions spanning 8K-2M-word contexts with deep multi-hop reasoning; humans score 53.7% under time pressure.
This entry links to an external website rather than a GitHub repository, so there's no README to display here.