Skip to main content

MazeBench

MazeBench is a local browser app for building and playing persistent 3D puzzle worlds, then evaluating coding agents in the same JavaScript engine.

Install

Python 3.9+ and Node.js are required.

pip install mazebench
mazebench launch

This opens the Play, Build, and Agent modes. Run mazebench --help for other commands.

Play directly in an ASCII terminal with arrow-key controls:

mazebench ascii
mazebench ascii --level CxD

Both CxD and the full level_CxD level ID are accepted.

Play interactively with the same controls while showing the structured JSON observation a model receives, with literal object names and every room object included:

mazebench json --level CxD --omniscient

Omit --omniscient to include only objects visible in the equivalent ASCII view. Names are not hidden unless --hide-names is passed explicitly. JSON arrays are kept on one line in the terminal. Pipe the output or pass --once to print a single snapshot instead of starting an interactive session.

Local agent runs also require Docker and either the Codex CLI or Claude Code. Replay video requires a Chromium-family browser and ffmpeg.

Website · Source

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mazebench-0.2.16.tar.gz (5.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mazebench-0.2.16-py3-none-any.whl (6.0 MB view details)

Uploaded Python 3

File details

Details for the file mazebench-0.2.16.tar.gz.

File metadata

  • Download URL: mazebench-0.2.16.tar.gz
  • Upload date:
  • Size: 5.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for mazebench-0.2.16.tar.gz
Algorithm Hash digest
SHA256 10b81cadf5b5ed1ae9fb199b34d2cfa69199fda832c0ae7a4a75f822b6ebce2d
MD5 5e8d34e4aaba7bdc614dda82995795b1
BLAKE2b-256 6727ede43e9f5a9556a4d0bd6b1e13c2107d69be00877b3c52ceca02f8e00b38

See more details on using hashes here.

Provenance

The following attestation bundles were made for mazebench-0.2.16.tar.gz:

Publisher: publish.yml on mazebench/MazeBenchEngine

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mazebench-0.2.16-py3-none-any.whl.

File metadata

  • Download URL: mazebench-0.2.16-py3-none-any.whl
  • Upload date:
  • Size: 6.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for mazebench-0.2.16-py3-none-any.whl
Algorithm Hash digest
SHA256 9190118d476e98dfb06d6908979844c0fdc4e73f795f7e15f0d7d79d508ee0a9
MD5 5be44342d2886d087de1b3da9b084c11
BLAKE2b-256 ffe264ef665b8aee93cbd55a3ab9c53b75c916af0ea8903e5b4bd7157679a34d

See more details on using hashes here.

Provenance

The following attestation bundles were made for mazebench-0.2.16-py3-none-any.whl:

Publisher: publish.yml on mazebench/MazeBenchEngine

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.2.19

2 files

0.2.18

2 files

0.2.17

2 files

This release

0.2.16 This release

2 files

0.2.15

2 files

0.2.14

2 files

0.2.13

2 files

0.2.12

2 files

0.2.11

2 files

0.2.10

2 files

0.2.9

2 files

0.2.8

2 files

0.2.7

2 files

0.2.6

2 files

0.2.5

2 files

0.2.4

2 files

0.2.3

2 files

0.2.2

2 files

0.2.1

2 files

0.2.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page