Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. AI
  4. /
  5. APEX Agents
AI
APEX Agents icon

APEX Agents

by Mercor

APEX-Agents is Mercor's benchmark of 480 tasks for testing whether AI agents can do long-horizon professional services work across applications. Tasks were written by investment banking analysts, management consultants and corporate lawyers.

Dataset·Free

View on Hugging Face(opens in a new tab)

About APEX Agents

Key features of APEX Agents

  • 480 tasks, 160 per job category
  • 33 worlds across banking, consulting and law
  • Binary rubric grading with a mean of about 4 criteria per task
  • Gold outputs provided for every task
  • World assets included as files and metadata
  • Worlds include tools such as mail, chat, calendar, spreadsheets and PDFs
  • Open-source agent execution service on GitHub
  • Live leaderboard on Hugging Face

Who APEX Agents is for

  • Teams evaluating AI agents on professional work
  • Researchers studying long-horizon tool use
  • Model developers benchmarking agent releases

How to use APEX Agents

  1. 1

    Step 1: Sign in to Hugging Face and accept the access conditions on the dataset page.

  2. 2

    Step 2: Load the data with load_dataset("mercor/apex-agents").

  3. 3

    Step 3: Set up the open-source execution service linked from the card to run your agent in each world.

  4. 4

    Step 4: Give the agent each task prompt and collect its output.

  5. 5

    Step 5: Grade the output against the rubric criteria with a judge model and compare against the leaderboard.

APEX Agents FAQ

Can I train on APEX-Agents?

No. The card says it is for model evaluation only and forbids training, fine-tuning or parameter fitting.

How are tasks graded?

A judge model grades each binary rubric criterion as met or not met, using the prompt, the agent output and relevant artifacts.

What license is it under?

CC-BY 4.0, with the evaluation-only restriction stated on the card.

Which jobs are covered?

Investment banking, management consulting and corporate law, with 160 tasks each.

Details

Pricing
FreeFree under CC-BY 4.0, for model evaluation only. Training, fine-tuning and scraping are forbidden, and access requires accepting conditions on Hugging Face.
Type
Dataset
Categories
AIDataResearch
Added
Sep 17, 2026
Mercor iconPublisherMercor

Built from public sources

We put this page together from APEX Agents’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with APEX Agents.

Work at APEX Agents? Claim the listing to manage it yourself.

Something wrong here?

More from Mercor

View publisher
Mercor AI Interviews iconMercor AI InterviewsMercor · Contact for pricingMercor AI Interviews applies AI to AI interviewing and matching workflow used to assess candidates and connect talent with suitable work opportunities.Business · Contact for pricingMercor iconMercorMercor · Contact for pricingMercor uses AI for AI-driven recruiting marketplace that evaluates, matches, and connects specialized talent with companies.Business · Contact for pricing

Related tools

See more
UnUniPhys-BenchSpatialVerse · FreeUniPhys-Bench is a human-verified benchmark of articulated 3D objects annotated with joint motion and physical properties. This repository holds the primary release of 1,473 objects.AI · FreeHH-RLHF iconHH-RLHFAnthropic · FreeHH-RLHF is Anthropic's dataset of human preference comparisons on helpfulness and harmlessness, plus red teaming transcripts. It is meant for research on making models less harmful.AI · FreePhysicalAI Autonomous Vehicles iconPhysicalAI Autonomous VehiclesNVIDIA · FreePhysicalAI Autonomous Vehicles is a gated NVIDIA dataset for developing autonomous vehicle and automated driving systems, released under the NVIDIA Autonomous Vehicle Dataset License Agreement.AI · Free