chini-001-url-shortener

URL Shortener (TinyURL)

Map long URLs to short tokens. Survive spike traffic on the redirect path.

Source: Classic system-design interview corpus (TinyURL / bit.ly clone)

Prompt

Design a URL shortener.

Functional:
- POST /shorten takes a long URL, returns a 7-character short code.
- GET /:code returns a 302 redirect to the original URL.
- The READ path (redirects) is 100x more frequent than writes.

Non-functional:
- p99 redirect latency must stay healthy under a 5x traffic spike.
- A cache outage must not bring down the system.

Return a Chinilla CanvasState that models the request flow end to end. Include at least one cache, at least one storage component, and a rate-limit or circuit-breaker behavior somewhere on the write path.

Constraints

Max components: 10
Required behaviors: storage, ratelimit
Monthly budget: $400

Stress scenarios

Baseline reads

baseline

Steady redirect traffic with no failures.

5x read spike

spike

Traffic suddenly multiplies 5x. Redirect path must hold.

Cache outage

outage

Cache layer disabled. All reads must fall through to storage.

Pass criteria (overall)

Min stability score: 70
Max drop rate: 5.0%
Min delivery rate: 90.0%
Max errors: 5

Submit your run

Submissions go through the chini-bench CLI. It calls your model with your key, scores the result locally, and posts to the leaderboard. Nothing leaves your machine except the canvas it produces.

End-to-end:

pip install git+https://github.com/collapseindex/chini-bench-cli.git
export OPENROUTER_API_KEY=...

chini-bench run chini-001-url-shortener \
  --provider openrouter --model google/gemini-2.0-flash-001 \
  --as alice --x alice --linkedin alice-builds

Or inspect the prompt first:

chini-bench prompt chini-001-url-shortener

Providers: openai · anthropic · google · openrouter · ollama

Leaderboard

Rank	Submitter	Model	Score	Stability	Delivery	Design	Pass	Links
#1	alex default	G google/gemini-3.1-pro-preview	89	77.0	100.0	75.0	✓	X
#2	alex default	A anthropic/claude-sonnet-4.6	63	25.0	100.0	100.0	✗	X
#3	alex default	X x-ai/grok-4.20	54	67.0	0.0	25.0	✗	X
#4	alex default	O openai/gpt-5.4	47	13.0	67.0	100.0	✗	X

Per-scenario breakdown of the top run

Scenario	Health	Drop rate	Delivered	Pass
baseline	79.0	3.1%	146	✓
5x-spike	74.0	4.9%	692	✓
cache-outage	77.0	0.0%	15	✓

How is this scored? →