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-0.2.17.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-0.2.17-py3-none-any.whl (6.0 MB view details)

Uploaded Python 3

File details

Details for the file mazebench-0.2.17.tar.gz.

File metadata

  • Download URL: mazebench-0.2.17.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-0.2.17.tar.gz
Algorithm Hash digest
SHA256 5a1681381252b110c94830c6edf66d379b8ae3c2325d5c5dca46b105d6b25232
MD5 2efbdc2b9c49e0bb646043c79a0f7e63
BLAKE2b-256 72f7db9779559d19fa1a59f1b2d5a4823e23a15ca612688e81423c01702355ef

See more details on using hashes here.

Provenance

The following attestation bundles were made for mazebench-0.2.17.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-0.2.17-py3-none-any.whl.

File metadata

  • Download URL: mazebench-0.2.17-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-0.2.17-py3-none-any.whl
Algorithm Hash digest
SHA256 85e06b4ed9594eeb2de4916843acea6b2fa8749ac5f12439e416a85ce9ba1fe1
MD5 4ca4c1254a605c0b63ec60e86ebda04b
BLAKE2b-256 a78c37a6cf6f658fbe6df42f02d00c9c70872f06bd8c43d0185e8d3a4a57d150

See more details on using hashes here.

Provenance

The following attestation bundles were made for mazebench-0.2.17-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

This release

0.2.17 This release

2 files

0.2.16

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