Benchmarks

TheAgentCompany

Self-contained workplace environment for evaluating agents on professional tasks involving websites, files, code, and simulated coworkers.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as Markdown Record JSON

What is this resource?

Resource type: Benchmarks
Environment: web, desktop
Topics: evaluation, workflow, cross-app
Record publication date: Not recorded
Evidence retrieved: 2026-10-16T10:42:34Z
Resource ID: github:theagentcompany/theagentcompany

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code: MIT (repository LICENSE header; not a weights/data license)
Data: Not recorded
Document: Not recorded
Weights: Not recorded

Evaluation protocol

Focus: professional workflows, multi-tool tasks
Setting: interactive
Observations: Not recorded
Actions / outputs: web browsing, code execution, coworker communication
Evaluation: Task-specific evaluator scripts run within the prepared workplace environment.

Scale and counting units

175 task images — workspace images documented by the README source

Each task is packaged as a Docker image. Record task-image and server versions; the environment includes simulated coworkers and external application state.

Compare source-reviewed profiles

Recorded specifications

leaderboard url: https://the-agent-company.com/#/leaderboard

Explore related topics

Evaluation Workflows Cross-app

Related resources

documented by: TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

editorial primary review
Retrieved 2026-10-16T10:42:34Z. Supports: name, kind, summary, environments, topics, scope, relations, details.benchmark_protocol, details.leaderboard_url.
Content fingerprint
d1646f67d49d38ef1e81bf7b5057dfc3d6f172b4c8a7413a2cc78741ccb08723
license header
Retrieved 2026-10-16T10:48:42Z. Supports: licenses.code.
Content fingerprint
2d6976a9b482bb14d9cd4f0d97ce6e14305496f1649b8667cb91d027c670930f

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.