Four-Factor Integrity Breakdown & Primary-Source Evidence
Access Model: Public Plaintext
"MMLU-Pro dataset is a more robust and challenging massive multi-task understanding dataset tailored to more rigorously benchmark large language models' capabilities. This dataset contains 12K complex questions across various disciplines."
Originality
Weight 25%
0/10
Reuse Profile: High Reuse (>75%)
"MMLU-Pro comprises over 12,000 rigorously curated questions from academic exams and textbooks, spanning 14 diverse domains including Biology, Business, Chemistry, Computer Science, Economics, Engineering, Health, History, Law, Math, Philosophy, Physics, Psychology, and Others."
Freshness
Weight 20%
0/10
Initial Release: 2024-06Latest Refresh: 2024-06Rolling Updates: No
"arXiv:2406.01574 (cs) [Submitted on 3 Jun 2024 ( v1 ), last revised 6 Nov 2024 (this version, v6)]"
Grading
Weight 15%
7.3/10
Integrity: Independent StandardizedSandbox: not applicable single turn
"10 option multiple choice format Regex-based answer extraction with pass@1 scoring (prompt and regex below)"
Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:
[](https://benchaudit.org/benchmarks/mmlu-pro/)