mmlu/high-school-biology
High school biology
Subject-level multiple-choice knowledge and reasoning questions.
Not yet importedNo sandbox required
MMLU
Upstream publisher UC Berkeleyhendrycks/test
Multiple-choice questions across academic and professional subjects, from elementary mathematics to law and medicine.
knowledgemultiple-choicechat
PROVENANCEUPSTREAM RECORD
- Upstream source
- hendrycks/test
- Trunchbull port
- Not packaged
- Version
- TEST / HEAD
- Release digest
- Not compiled
- License
- Source terms
Source commit: Upstream head not pinnedPublished Indexed July 30, 2026
WHAT THIS PROJECT MEASURES
README
MMLU is a broad knowledge and reasoning benchmark organized into subject-level datasets. A useful release must preserve subject labels, answer-choice ordering, split provenance, and the exact scoring convention.
This is a comparatively simple registry import: static prompts, fixed labels, no model tools, and no execution environment. Trunchbull has not yet compiled an immutable release.
EXECUTION CONTRACT
Prompt-and-label import with exact answer-choice grading. No sandbox or model tools required.
TRUNCHBULL AVAILABILITY
Import status
Not yet imported
Not yet imported. The first release needs pinned subject files, deterministic prompt rendering, and exact answer-choice grading.
Port this benchmark2 CASES
Evaluation cases
2
Chat lane
mmlu/professional-law
Professional law
Professional-domain questions with a fixed four-choice answer set.
0 REQUESTED TOOLS
Tools
0
No model tools required.
Evaluation happens through the prompt and grader contract for this release.
MACHINE-READABLE PROVENANCE
Registry record
{
"name": "MMLU",
"catalogOwner": null,
"source": {
"url": "https://github.com/hendrycks/test",
"version": "Upstream test repository",
"commit": "Upstream head not pinned",
"license": "Source terms"
},
"port": null,
"release": {
"digest": "Not compiled",
"lane": "chat",
"sandboxRequired": false
},
"cases": [
"mmlu/high-school-biology",
"mmlu/professional-law"
],
"tools": []
}BUILD ON THIS PROJECT