Datasets › MMLU-Pro

MMLU-Pro

Introduced by YuBo Wang et al. in MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark3 Jun 2024 archive 2025-07-28

The MMLU-Pro dataset is an enhanced version of the Massive Multitask Language Understanding (MMLU) benchmark. It's designed to be more robust and challenging, aiming to rigorously benchmark large language models' capabilities in language comprehension and reasoning across diverse domains. Here are some key features of the MMLU-Pro dataset:

  • Increased Complexity: It includes more reasoning-focused questions and expands the choice set from four to ten options, reducing the likelihood of random guessing and increasing the evaluation's complexity¹.
  • Elimination of Trivial Questions: MMLU-Pro removes trivial and noisy questions found in the original MMLU, making it a more discriminative benchmark².
  • Stability Under Varying Prompts: The dataset shows greater stability under varying prompts, with a decreased sensitivity of model scores to prompt variations².
  • Better Performance with Reasoning: Models utilizing Chain of Thought (CoT) reasoning achieved better performance on MMLU-Pro compared to direct answering².
  • Size and Scope: The dataset contains 12K complex questions across various disciplines¹⁴.

(1) TIGER-Lab/MMLU-Pro · Datasets at Hugging Face. https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro. (2) MMLU-Pro: A More Robust and Challenging Multi-Task Language .... https://arxiv.org/abs/2406.01574. (3) MMLU-Pro: An Upgraded Version of the MMLU Dataset | LLM Explorer Blog. https://llm.extractum.io/static/blog/?id=mmlu-pro-benchmark. (4) TIGER-Lab Introduces MMLU-Pro Dataset for Comprehensive Benchmarking of .... https://www.marktechpost.com/2024/05/16/tiger-lab-introduces-mmlu-pro-dataset-for-comprehensive-benchmarking-of-large-language-models-capabilities-and-performance/. (5) undefined. https://doi.org/10.48550/arXiv.2406.01574.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
MMLU MMLU-Pro Orange-mini 0-shot MRR 99.19 MyGO Multiplex CoT: A Method for Self-Reflection in... data-dream-gdsp/Multiplex-CoT 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran: none of the 1 papers with a benchmark row has a Syntology run on record

Page 1 of 1: paper 1 of 1 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 150. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking 1 1 20 Jan 2025 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MMLU-Pro

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections