HF dataset

SakanaAI / ChouBun

ChouBun is a Japanese-language long‑context benchmark for LLMs featuring two task types—extractive QA (wiki_qa, edinet_qa) and abstractive summarization (corp_sec_qa, corp_sec_sum)—built from Wikipedia articles, EDINET security reports, and corporate documents, with standardized THUDM/LongBench format and up to 32768‑token contexts.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
103
Hugging Face likes
10
Listed
Oct 22, 2024

Downloads (30-day window) over time

100120140160NovSepJulMayMarJan 2026103
Show as a table
MonthDL (30d)
Dec 2025113
Jan 2026—
Feb 2026—
Mar 2026—
Apr 2026—
May 2026—
Jun 2026—
Jul 2026156
Aug 2026—
Sep 2026—
Oct 2026—
Nov 2026103

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Learn from slides & articles