---
format: "aidr-story-markdown/v1"
id: "b28e2d9a0bfeae15e9491c1b750c70f832491604d59d15439caa96a5eeb8fdd5"
canonical_url: "https://aidr.today/b28e2d9a?lang=en"
title: "MMDM: Measuring Massive Multitask Decision Making"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-11T00:00:00.000Z"
category: "Data"
topics: ["llm","data-engineering"]
source_urls: ["https://huggingface.co/papers/2611.14309"]
summary: "MMDM (Massive Multitask Decision Making) is a benchmark of 5,448 high-quality questions across 16 task categories, combining newly constructed tasks with source-grounded recompositions and rewrites for single-select, multi-select, and soft-label decision making in fresh contexts. It covers realistic scenarios such as agent state tracking, tool and skill selection, preference judgments, and rubric scoring, with option spaces ranging from 2 to 1,024 and inputs extending to 64,817 tokens."
---

# MMDM: Measuring Massive Multitask Decision Making

> [Open the canonical story](<https://aidr.today/b28e2d9a?lang=en>)

**Published:** 2026-11-11T00:00:00.000Z
**Category:** Data
**Topics:** llm, data\-engineering

## Summary

MMDM \(Massive Multitask Decision Making\) is a benchmark of 5,448 high\-quality questions across 16 task categories, combining newly constructed tasks with source\-grounded recompositions and rewrites for single\-select, multi\-select, and soft\-label decision making in fresh contexts\. It covers realistic scenarios such as agent state tracking, tool and skill selection, preference judgments, and rubric scoring, with option spaces ranging from 2 to 1,024 and inputs extending to 64,817 tokens\.

## Sources

- [Story source](<https://huggingface.co/papers/2611.14309>)