Verified claim · AI-ML · 100% confidence
LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28).
Last verified 2026-05-16 · Methodology veritas-v0.1 · a41ff9e64baa566f
Structured fields
- Subject
- LongBench
- Predicate
introduced_in_paper- Object
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)
- Confidence
- 100%
- Tags
- longbench · thu · benchmark · long-context · evaluation · 2023
Sources (2)
[1] preprint · arXiv · 2023-08-28
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding“LongBench is the first bilingual, multitask benchmark for long context understanding, covering 21 datasets across 6 task categories in English and Chinese.”
[2] github release · THUDM (Tsinghua KEG) · 2023-08-28
LongBench — official GitHub repository
Cite this claim
Ready-to-paste citation (Markdown / plain text):
LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28). — SourceScore Claim a41ff9e64baa566f (verified 2026-05-16). https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/a41ff9e64baa566f/" width="100%" height="360" frameborder="0" loading="lazy" title="LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
SWE-bench introduced in: Jimenez et al. 2024 — software engineering benchmark from GitHub issues.
b16b5f5297e5f621 · 100% confidence · shares 3 tags (benchmark, evaluation, 2023)
LMArena (Chatbot Arena) founded in: 2023 — LMSYS Chatbot Arena → LMArena.ai 2024.
88ff5918737d7b6b · 100% confidence · shares 3 tags (evaluation, benchmark, 2023)
MMLU benchmark introduced in paper: Measuring Massive Multitask Language Understanding (Hendrycks et al., 2020).
428d754e7c651be6 · 100% confidence · shares 2 tags (benchmark, evaluation)
SuperGLUE benchmark introduced in paper: SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems (Wang et al., 2019).
1a1e87145608c91a · 100% confidence · shares 2 tags (benchmark, evaluation)
GLUE benchmark introduced in paper: GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (Wang et al., 2018).
aa113b5e61d5c214 · 100% confidence · shares 2 tags (benchmark, evaluation)
Frequently asked questions
Is the claim "LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)."?
Evidence comes from 2 primary sources: arXiv, THUDM (Tsinghua KEG). Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "LongBench introduced in paper: LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Bai et al., THU + Zhipu AI 2023-08-28)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_longbench_fact() -> dict:
"""Fetch the verified SourceScore claim for LongBench."""
r = httpx.get("https://sourcescore.org/api/v1/claims/a41ff9e64baa566f.json")
return r.json()