Datasets › MML
MML (Massive Multitask Language Understanding)
MMLU (Massive Multitask Language Understanding) is a new benchmark designed to measure knowledge acquired during pretraining by evaluating models exclusively in zero-shot and few-shot settings. This makes the benchmark more challenging and more similar to how we evaluate humans. The benchmark covers 57 subjects across STEM, the humanities, the social sciences, and more. It ranges in difficulty from an elementary level to an advanced professional level, and it tests both world knowledge and problem solving ability. Subjects range from traditional areas, such as mathematics and history, to more specialized areas like law and ethics. The granularity and breadth of the subjects makes the benchmark ideal for identifying a model’s blind spots.
Image source: https://arxiv.org/pdf/2009.03300v3.pdf
Benchmarks archive 2025-07-28
All 29 leaderboards 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.
Syntology 82 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Multi-task Language Understanding · MML (59 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (College Biology) (5 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Medical Genetics) (3 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Professional medicine) (1 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Formal Logic) (1 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Abstract Algebra) (2 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Econometrics) (1 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (High School Computer Science) (1 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (College Mathematics) (4 judged, 0 placed), Multiple Choice Question Answering (MCQA) · MMLU (Astronomy) (1 judged, 0 placed), Multi-task Language Understanding · MMLU (5-Shot) (16 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Papers archive 2025-07-28
papers with a benchmark row: 25 · with a code link: 21 · where Syntology ran a sample: 13 (13 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 (13 of 25 with a benchmark row: 13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25 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 1,922. 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.
Dataset loaders archive 2025-07-28
11 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- mmlu
- MMLU TR v0.2
- MMLU TR
- MMLU (5-Shot)
- MMLU (College Medicine)
- MMLU (Professional medicine)
- MMLU (Anatomy)
- MMLU (Clinical Knowledge)
- MMLU (Medical Genetics)
- MMLU (Mathematics)
- MMLU (Machine Learning)
- MMLU (High School Statistics)
- MMLU (High School Physics)
- MMLU (High School Mathematics)
- MMLU (High School Computer Science)
- MMLU (High School Chemistry)
- MMLU (High School Biology)
- MMLU (Formal Logic)
- MMLU (Elementary Mathematics)
- MMLU (Electrical Engineer)
- MMLU (Econometrics)
- MMLU (College Physics)
- MMLU (College Mathematics)
- MMLU (College Computer Science)
- MMLU (College Chemistry)
- MMLU (College Biology)
- MMLU (Astronomy)
- MMLU (Abstract Algebra)
- MML
29 variant names, 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