Skip to content
Pac-Bench

Free alternatives to Pac-Bench

200 free apps like Pac-Bench, closest match first.

Top picks

  1. A

    AI Gallery

    Launch

    This site is a collection of open source classic games and puzzles written in React that you can play for free in the browser. It includes Minesweeper with custom board size and mine count, a sliding number puzzle that can show a solution,

    FreeOpen source

  2. T

    TetrisBench

    Launch

    TetrisBench is a Tetris match where a human plays against AI models. You sign in, pick a player, and battle a model on a timed board, with a two-minute clock and a score, lines and level for each side. The AI opponents listed on the site in

    Free

  3. B

    Benchmark Heaven

    Launch

    Benchmark Heaven compares AI models on cost and capability, with benchmark results, charts and provider prices. It is the home of JevBench, a decision-model benchmark that measures accuracy, calibration, latency and cost. The site has a cos

    Free

  4. G

    GameBlocks

    Launch

    Concise, self-explanatory building blocks for AI coding agents to prototype browser-based 3D games.

    FreeOpen source

  5. N

    Noobi.ai

    Launch

    Noobi.ai is a local desktop agent that turns a game idea into a playable browser game. You describe the game in a prompt, and the agent chooses a Web project or a Godot 4 project and builds it inside an isolated project folder. The work run

    FreeOpen source

  6. M

    MagicArena

    Launch

    MagicArena is a Chinese-language public arena for visual AI models. You enter a prompt and compare the outputs of different image and video generation models side by side, with models such as Midjourney, FLUX, Kling, Hailuo and Jimeng named

    Free

More like Pac-Bench

7
P

Pixtuoid

Terminal pixel-art office for AI coding agents

Launch
8
P

Petdex

A public gallery of animated pets for Codex, Claude Code, DeepSeek Harness

Launch
9
A

Agent Town

A pixel-art AI agent online collaboration platform

Launch
10
A

Agentic Vbench

AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?

Launch
11
P

Packmind

Packmind seamlessly captures your engineering playbook

Launch
12
D

Domscribe

Pixel-to-code bridge that captures runtime context

Launch
13
P

ParseBench

A Document Parsing Benchmark for AI Agents

Launch
14
A

Age Of Agents

Watch your AI coding sessions grow a peaceful pixel-art realm

Launch
15
W

WritingBench

A Comprehensive Benchmark for Generative Writing

Launch
16
P

Pagenodes

Completely Browser Based AI and IoT Platform

Launch
17
J

Jumping-Agent-platform

Build your own AI agent through gameplay

Launch
18
P

Psters_AI_Workflow

An auto-documenting, model-agnostic AI workflow for any project, framework

Launch
19
W

Wai Play

AI web game testing and quality evaluation platform

Launch
20
P

Pipelex

Build AI methods with your coding agent

Launch
21
P

PromptScript

Prompt-as-Code for Enterprise AI

Launch
22
U

UltraGameStudio

AI coding agent for game development: engine workflows…

Launch
23
B

Brainwave

Modern Animated SaaS Generative AI Landing Page

Launch
24
C

Cve Bench

CVE-Bench: A Benchmark for AI Agents’ Ability

Launch
25
P

PI WEB

Web UI for Pi Coding Agent that keeps sessions alive in real workspaces

Launch
26
L

LocalMode

Run AI entirely in your browser, no servers or API keys

Launch
27
P

pacman

Retro arcade-inspired design

Get
28
P

Pentest Harness

Heaven for Hackers

Launch
29
A

Agentpet

A desktop pet for macOS & Windows that monitors your AI coding agents

Launch
30
M

Macos Portfolio

A fully responsive, open-source macOS-inspired developer portfolio

Launch
31
P

Primitive Bench

The marketplace for verifiable AI outcomes: state a task

Launch
32
P

Pocketpaw

Your AI agent in 30 seconds

Launch
33
A

AgentDeck

Local dashboards and physical controls for AI coding agents

Launch
34
D

Design Arena

Design Arena is the largest global crowdsourced benchmark for design

Launch
35
N

Nimbalyst

A visual workspace for managing AI coding sessions, tasks, and project files

Launch
36
P

Prompttools

Open-source tools for prompt testing and experimentation

Launch
37
H

Harness Score

Your AI coding agent is only as reliable as the harness around it

Launch
38
A

AI LLM Comparison

A website where you can compare every AI Model

Launch
39
P

Promptus

Create AI videos, images, audio, 3D, and more

Launch
40
A

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Launch
41
A

AGHub

One hub for every AI coding agent

Launch
42
B

BOSS Console

Open-source, multi-platform harness for AI agents

Launch
43
C

Codemap

a project brain for your AI

Launch
44
P

Prompticus

Find, save, and share AI prompts and MCP servers in one place

Launch
45
H

harness-creator

Build, audit, and improve harnesses

Get
46
T

The Pair

Open-source AI pair programming for desktop: a Mentor + Executor agent…

Launch
47
C

Core

chaicore - open-source AI-enabled visual website builder for Next.js

Launch
48
A

AgentOp

Run a real LLM in your browser. No install, no server

Launch
49
Y

Your-source-to-prompt.html

Quickly and securely turn your code projects into LLM prompts

Launch
50
S

System Prompts And Models Of AI Tools

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI

Launch

About Pac-Bench

P

Pac-Bench

PacBench: how well a model and harness can recreate Pac-Man from a single prompt

PacBench is a web gallery that compares how well different AI models and coding harnesses can build a Pac-Man game from one short prompt: create a Pac-Man game in a single HTML page. Each entry is shown as a card that you can open and play, and the gallery can be searched, filtered by model, and sorted by score, cost, time, tokens or release date. Where the harness transcripts allow, cards record wall time, token counts, cost and the size of the generated HTML file. The notes explain how runs were made, for example that some phases used Claude Code pointed at OpenRouter, others used Antigravity with Gemini, and how costs were calculated for particular entries. It is a useful reference for developers curious how coding agents compare on a small, self-contained game task, and the source is on GitHub.

Category
AI
Website
jonclegg.github.io