textTIGER-Lab/MMLU-Prollm-evalbenchmarkmmluquestion-answeringreasoningmultiple-choiceenglishmit-license

MMLU-Pro: Robust Multi-Task LLM Benchmark (12K Questions)

Category
Text
Records
12,102 rows
Format
PARQUET
Update Frequency
One-time snapshot
Collection Method
auto_imported_huggingface_federated
PII
None detected
File Size
~3.99 MB
Downloads
0

About this data

12K challenging multi-discipline multiple-choice questions for benchmarking LLM reasoning. MIT-licensed, parquet format, widely used for model evaluation and leaderboards.

Schema

NameTypeDescription
question_idBIGINTUnique integer identifier for each question in the dataset
questionVARCHARQuestion prompt text, may include LaTeX mathematical notation
optionsVARCHAR[]Array of up to 10 candidate answer choice strings (A–J)
answerVARCHARCorrect answer as a single letter (A–J)
answer_indexBIGINTZero-based integer index of the correct option in the options array
cot_contentVARCHARChain-of-thought reasoning trace or explanation (may be empty)
categoryVARCHARSubject discipline: math, physics, chemistry, law, engineering, psychology, health, business, biology, philosophy, economics, history, or computer science
srcVARCHAROriginal source or dataset origin (e.g., cot_lib-abstract_algebra, MMLU, TheoremQA, SciBench)

Sample Data

Preview a sample of the data before downloading.

Free

Open dataset

Quality: No ratings
0 downloads
Seller: DataBazaar
Sign up to download

Agent? No sign-up needed →

For AI Agents

Via MCP Server
# 1. Add to your agent's MCP config (claude_desktop_config.json or similar):
{
  "mcpServers": {
    "databazaar": { "command": "npx", "args": ["databazaar-mcp"] }
  }
}

# 2. Your agent can then call:
search_datasets({ query: "MMLU-Pro: Robust Multi-Task LL" })
// Found: b238a99d-d860-4b47-8ec6-9708ef72f5db
get_download_url({ dataset_id: "b238a99d-d860-4b47-8ec6-9708ef72f5db" })  // free — no API key needed
Via REST API
# Free dataset — no API key required:
curl https://api.databazaar.io/datasets/b238a99d-d860-4b47-8ec6-9708ef72f5db/download-url