Verified claim · AI-ML · 92% confidence
MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024).
Last verified 2026-05-31 · Methodology veritas-v0.1 · 2df92e0b0e4c891b
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- MMLU-Pro benchmark
- Predicate
introduced_in_paper- Object
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)
- Confidence
- 92%
- Tags
- mmlu-pro · benchmark · evaluation · reasoning · wang · 2024
Sources (3)
[1] preprint · arXiv (Yubo Wang et al. — TIGER-Lab) · 2024-06-03
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark“This paper introduces MMLU-Pro, an enhanced dataset designed to extend the mostly knowledge-driven MMLU benchmark by integrating more challenging, reasoning-focused questions”
[2] github release · TIGER-AI-Lab · 2024-06-03
MMLU-Pro official repository (NeurIPS 2024)[3] model card · Hugging Face
MMLU-Pro dataset cardHugging Face is rated by SourceScore — see its reliability →
Cite this claim
Ready-to-paste citation (Markdown / plain text):
MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024). — SourceScore Claim 2df92e0b0e4c891b (verified 2026-05-31). https://sourcescore.org/api/v1/claims/2df92e0b0e4c891b.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/2df92e0b0e4c891b/" width="100%" height="360" frameborder="0" loading="lazy" title="MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
GPQA benchmark introduced in paper: GPQA: A Graduate-Level Google-Proof Q&A Benchmark (Rein et al., 2023).
26f75f130f7b395a · 92% confidence · shares 3 tags (benchmark, evaluation, reasoning)
LiveCodeBench introduced in paper: LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (Jain et al., 2024).
b474cbe11ab65d51 · 92% confidence · shares 3 tags (benchmark, evaluation, 2024)
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 "MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)." verified?
Yes — SourceScore verified this claim with 92% confidence as of 2026-05-31. The verification uses 3 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 "MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)."?
Evidence comes from 3 primary sources: arXiv (Yubo Wang et al. — TIGER-Lab), TIGER-AI-Lab, Hugging Face. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/2df92e0b0e4c891b.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-31 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/2df92e0b0e4c891b.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/2df92e0b0e4c891b.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/2df92e0b0e4c891b.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/2df92e0b0e4c891b.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "MMLU-Pro benchmark introduced in paper: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (Wang et al., 2024)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_mmlu_pro_benchmark_fact() -> dict:
"""Fetch the verified SourceScore claim for MMLU-Pro benchmark."""
r = httpx.get("https://sourcescore.org/api/v1/claims/2df92e0b0e4c891b.json")
return r.json()