★
Menu
Home How It's Built Watchlist The Stack
Hardware ChipsCompare Chips Servers & SystemsNetworking MemoryFoundries & Packaging Cooling
Facilities Data CentersPower ProjectsCloud & GPU Compute
Intelligence AI ModelsSoftware AI ProductsBenchmarks Research PapersDatasets Concepts
Ecosystem CompaniesStocks PeopleTimeline TrendsFuture of AI
Learn News Ask the Data AI Agents
About About us Methodology Data & API Disclaimer
Options
DATA & API

Free read-only JSON access to the site's cached data.

Dark mode

Guided View
New to chips, data centers and model jargon? We explain key terms as you browse, in plain English. Same data, with the help built in.

Expert View
You already know the stack. Just the data: clean, fast and compact, with no extra explanations. This is the default view.

Interface language
‹ Back
Home › Benchmarks › MMLU & MMLU-Pro

MMLU & MMLU-Pro

Benchmark Capability

The default knowledge exam of 2020–24 — now saturated.

You're looking at a benchmark record: a test the industry uses to measure chips or models — and what it actually tells you.

MMLU's 57-subject multiple-choice exam was the standard capability score from GPT-3 (43.9%) to the high-80s frontier plateau; MMLU-Pro hardened it as scores saturated. Its arc is the pattern every benchmark follows: introduced, climbed, saturated, replaced.

How this connects to the rest of the stack

Related · 1 MMLU & MMLU-Pro

This record's links at a glance — click a group to jump to it.

Related

Sources

MMLU paper ↗

Record reviewed as of 2026-01-15 — see Methodology.