
Vibe coding benchmarks for real life.
Every new AI model, the most popular tests plus the most useful everyday ones. See what it builds.
The Classic Pelican SVG
The one-line drawing test the whole internet gives every new AI.
Jelly Orange Slice
A glossy orange slice made of jelly. Poke it, squeeze it, watch it wobble.
Swim the Kelp Garden
A whole kelp forest under the sea, made only from code. Swim through it with one finger.
Build a Cell, Part by Part
Watch a living cell build itself one part at a time, then tap any part to learn what it does.
The Most Uncomfortable Web Page
Everything is a little wrong on purpose. How long can you stand it?
Pelican on a Bike
Ring the bell, then drag the speed slider.
The Flan Test
Tap Shake the plate, then scoop it with the Spoon.
Notebook Mini-Golf
Drag back from the ball like a slingshot, let go.
Build-a-Box Bakery
Pick a box of 12, then tap pastries to fill it.
Aurora Over a Frozen Lake
Tap Shooting star, then try Long exposure.
Why the Moon Has Phases
Tap +1 day and watch the phase change.

Same prompt, other AIs
AnthropicClaude · Claude Code17 runs
- Fable 5.2works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Haiku 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Sonnet 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Opus 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
OpenAIChatGPT · Codex20 runs
- GPT-6.2 Astraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.2 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Terraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
AnthropicClaude · Claude Code17 runs
- Fable 5.2works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Haiku 5.5partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Sonnet 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)no file
- Opus 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
OpenAIChatGPT · Codex20 runs
- GPT-6.2 Astraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.2 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Terraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)no file
- GPT-6.1 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
AnthropicClaude · Claude Code17 runs
- Fable 5.2works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Haiku 5.5partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Sonnet 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Opus 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
OpenAIChatGPT · Codex20 runs
- GPT-6.2 Astraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.2 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Terraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
AnthropicClaude · Claude Code17 runs
- Fable 5.2works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Haiku 5.5broken · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Sonnet 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Opus 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
OpenAIChatGPT · Codex20 runs
- GPT-6.2 Astraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)partly works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.2 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Terraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)broken · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
AnthropicClaude · Claude Code17 runs
- Fable 5.2works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Haiku 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Sonnet 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- Opus 5.5works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
OpenAIChatGPT · Codex20 runs
- GPT-6.2 Astraworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.2 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Terranot checked yetworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
- GPT-6.1 Solworks · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)works · auto-checked (Checked by an automated pass. Not hand-played yet.)
AnthropicClaude · Claude Code7 runs
- Sonnet 5.5Effort: High, level 3 of 5works · 1 try
- Opus 5.5works · try 1 of 2works · try 1 of 2works · 1 tryworks · 1 tryno file
- Fable 5.1Effort: High, level 3 of 5works · 1 try
AnthropicClaude · Claude Code3 runs
- Sonnet 5.5Effort: High, level 3 of 5works · try 1 of 2
- Opus 5.5Effort: High, level 3 of 5works · try 1 of 2
- Fable 5.1Effort: High, level 3 of 5works · try 1 of 2
AnthropicClaude · Claude Code3 runs
- Sonnet 5.5Effort: High, level 3 of 5works · try 1 of 2
- Opus 5.5Effort: High, level 3 of 5works · try 1 of 2
- Fable 5.1Effort: High, level 3 of 5works · try 1 of 2
AnthropicClaude · Claude Code3 runs
- Sonnet 5.5Effort: High, level 3 of 5works · try 1 of 2
- Opus 5.5Effort: High, level 3 of 5works · try 1 of 2
- Fable 5.1Effort: High, level 3 of 5works · try 1 of 2
AnthropicClaude · Claude Code1 run
- Opus 5.5Effort: High, level 3 of 5works · try 1 of 2
AnthropicClaude · Claude Code1 run
- Opus 5.5Effort: High, level 3 of 5works · try 1 of 2
| Anthropic103 runs | OpenAI100 runs | Google0 runs | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Benchmark | Fable 5.2 | Haiku 5.5 | Sonnet 5.5 | Opus 5.5 | Fable 5.1 | GPT-6.2 Astra | GPT-6.2 Sol | GPT-6.1 Terra | GPT-6.1 Sol | Gemini 4 Neonnot run yet | Runs |
| The Classic Pelican SVG | not run yet | not run yet | 37 | ||||||||
| Pelican on a Bike | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 7 | |||
| The Most Uncomfortable Web Page | not run yet | not run yet | 37 | ||||||||
| The Flan Test | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 3 | |||
| Build-a-Box Bakery | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 3 | |||
| Notebook Mini-Golf | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 3 | |||
| Aurora Over a Frozen Lake | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 1 | |
| Why the Moon Has Phases | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | not run yet | 1 | |
| Swim the Kelp Garden | not run yet | not run yet | 37 | ||||||||
| Build a Cell, Part by Part | not run yet | not run yet | 37 | ||||||||
| Jelly Orange Slice | not run yet | not run yet | 37 | ||||||||
| Runs | 10 | 25 | 29 | 35 | 4 | 25 | 25 | 25 | 25 | 0 | 203 |
Next up
Guess the model
Two AIs, names hidden.


Which one did Claude Sonnet 5.5 make?
prompt: Pelican on a Bike
Play more rounds