TIGER-Lab

license

MIT(OSI/open,redistributable)

access

public(not gated)

datasheet

present(comprehensive card+leaderboard)

splits

public(test+validation, no hidden held-out)

Fully open: MIT, ungated, redistributable, comprehensive card.

• https://arxiv.org/abs/2406.01574 recorded 2026-09-29

  The abstract describes MMLU-Pro as expanding the choice set "from four to ten options" and eliminating trivial and noisy MMLU questions.

• https://huggingface.co/api/datasets/TIGER-Lab/MMLU-Pro recorded 2026-09-29

  The Hugging Face API record for the dataset reads `license:mit` in its tags and `"gated":false`, with test and validation splits and the card text "MMLU-Pro dataset is a more robust and challenging massive multi-task understanding dataset".

• https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro recorded 2026-09-29

  The dataset page carries the tag `license:mit`, the card opens with "MMLU-Pro dataset is a more robust and challenging massive multi-task understanding dataset", and it describes an "Expert Review:" step with "rigorous scrutiny by a panel of over ten experts"; the leaderboard link renders.

Adoption is measured by Hugging Face downloads of TIGER-Lab/MMLU-Pro. MMLU-Pro is a standard knowledge-and-reasoning benchmark cited across frontier model reports.

• https://huggingface.co/api/datasets/TIGER-Lab/MMLU-Pro recorded 2026-08-12

  170,681 downloads in the trailing 30 days for TIGER-Lab/MMLU-Pro

A dataset is not 'capable', so capability is left unscored; openness and adoption carry this category.

• https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro recorded 2026-09-29

  The page shows a static question corpus with "MMLU-Pro dataset is a more robust and challenging massive multi-task understanding dataset" and a "Downloads last month" panel. Searched the body for throughput, latency, accuracy claims by the dataset itself: none; it is data, not a capable system.