✦ ONE BRIEF · ZERO HUMAN HELP · ONE FINAL APP

See what AI coding agents
can actually ship.

We test AI coding agents so you don't have to. We give coding agents the same complete product brief, provide zero human help, and evaluate the final apps they actually ship. 1 Prompt. 1 App. 0 Help.

2 Benchmarks Live
6 Total Agent Runs
100% Autonomous (0 Hints)
Tier 1 & 2 Models Evaluated

Active Benchmarks

Real-world coding agent ship-readiness evaluations
game-micro-tower-defense-v0 3 / 3 Shipped Tier 2 (Workhorse / Medium)

Micro Tower Defense Game

Full Game Benchmark Report →

A single-file HTML5 Canvas Tower Defense game requiring 60fps loop, 3 distinct tower types, upgrade/sell mechanics, wave management, particle explosions, and Web Audio API procedural sound synthesis.

🎬 16:9 2x2 Battle Grid Comparison

Gemini 3.7 Flash

Antigravity CLI · medium
⚡ 200s (Fastest)
200.0s Wall Time
339 tok/s Speed (TPS)
~$0.04 Est. Cost
55 KB Build Size
⚡ Cyberpunk Theme: Full Web Audio synthesizer, speed toggle (1x/2x/4x), rich upgrade dock.

GPT-5.6 Luna

Codex CLI · medium
📦 20 KB (Compact)
208.5s Wall Time
105 tok/s Speed (TPS)
~$0.22 Est. Cost
20 KB Build Size
✅ Compact Build: Minimalist single-file Canvas mechanics, persistent high scores.

Claude Sonnet 5

Claude Code · medium
🛡️ Self-Healed
951.9s Wall Time
65 tok/s Speed (TPS)
~$0.95 Est. Cost
48 KB Build Size
✅ Self-Healing: Tested via headless Chrome DevTools, fixed 2 bugs autonomously.
game-micro-3d-kart-v0 4 / 4 Shipped Tier 2 (Workhorse / Medium) Three.js 3D Engine

Micro 3D Arcade Kart Racing (Three.js)

Full 3D Game Report →

A single-file 3D Arcade Kart Racing game with procedural Three.js low-poly models, closed-loop stunt circuit, drift physics, tire smoke particles, 2 AI rival karts, 3-lap race system, boost pads, and real-time Web Audio sound synthesis.

🎬 16:9 2x2 Battle Grid (4 Models Active Playthrough)
</> Embed & Details

Gemini 3.7 Flash

Antigravity CLI · medium
⚡ 102s (Fastest)
102.2s Wall Time
252 tok/s Speed (TPS)
~$0.01 Est. Cost
70 KB Build Size
⚡ Stunt Circuit: Closed-loop track curves, dynamic FOV boost surge, 2 AI rivals, minimap radar.

Gemini 3.8 Flash

Antigravity CLI · medium
🚀 305 tok/s (Top TPS)
292.3s Wall Time
305 tok/s Speed (TPS)
~$0.07 Est. Cost
74 KB Build Size
🚀 Elevation & Nitro: Rolling terrain track, speed lines, 3-lap telemetry, high-performance 3D racer.

GPT-5.6 Luna

Codex CLI · medium
📦 25 KB (Compact)
522.0s Wall Time
42 tok/s Speed (TPS)
~$0.27 Est. Cost
25 KB Build Size
✅ Neon Apex: Retro-futuristic night track, countdown 3-2-1, procedural audio, compact single file.

Claude Sonnet 5

Claude Code · medium
🏎️ Grand Prix (Physics)
578.0s Wall Time
108 tok/s Speed (TPS)
~$1.01 Est. Cost
71 KB Build Size
✅ Grand Prix Track: Banking turns, drift smoke, check arch, dynamic speedometer & analog needle.
pilot-expense-tracker-v0 3 / 3 Shipped 2 / 3 Logic Defect

Personal Expense Tracker

View Expense Report →

A single-file HTML expense tracker requiring localStorage persistence, category dropdowns, dynamic budget warnings, and a running total of all expenses. Handed headlessly to 3 Tier 1 agent CLIs.

Explore Run Report & Comparison Matrix →

Benchmark Methodology

Strict experimental constraints for reproducible results
RULE 01

One Frozen Product Brief

Each agent receives an unedited, exhaustive product specification once. Zero human semantic follow-ups, zero steering, and zero debugging hints.

RULE 02

Autonomous Headless Execution

The agent plans, codes, inspects, and verifies on its own inside an isolated sandbox. Exact harness versions, models, and environments are recorded.

RULE 03

Verifiable Artifacts & Telemetry

We capture exact wall-clock durations, token consumption, session transcripts, and unedited code outputs so claims can be audited independently.

</> Embed 1P1A Widget

Copy this responsive HTML iframe snippet into your Substack, Blog, or Website: