CODEVARENAbenchmark-001
BENCHMARK-001 · 4 SNIPPETS · 25s EACH
BENCHMARK-001 · 4 SNIPPETS · 25s EACH

Most devs ship whatever the AI writes.
Prove you don't.

Four short snippets — Python, TypeScript, JavaScript, Go, SQL, Java. Some hide real bugs — some are clean. Flag what's broken before the clock runs out — or they ship with your name on the commit.

no login · no retries
No cookies, no tracking. What we store.
codevarena — session log
» benchmark-001 queued
→ loading 4 AI-written snippets…
→ some contain real bugs
→ 25s per snippet | retries: 0

The 90-second AI code review benchmark

CodevArena tests one specific skill: whether you can tell working AI-generated code from code that only looks like it works. It takes about ninety seconds, needs no account, and gives you a shareable scorecard with a real percentile at the end.

What is the AI Bug Hunt?
A free 90-second benchmark that measures whether you can spot bugs in code written by an AI. You are shown four short snippets. Some contain a real defect, some are clean, and you are never told how many of each. For each one you either flag the broken line and say what is wrong with it, or ship it as correct.
Why does it matter whether you can review AI-generated code?
Coding assistants now write a large share of the code that reaches production, and reviewing a diff is a different skill from writing the code yourself. The common failure is accepting a plausible-looking suggestion without verifying it. The second, less discussed failure is the opposite: blocking correct code because it looks unfamiliar. This benchmark measures both.
Which languages does it cover?
Python, TypeScript, JavaScript, Go, SQL, and Java. Every snippet is chosen to be readable in under fifteen seconds by a developer who does not write that language, so the test measures code review rather than language trivia.
What kinds of bugs does it use?
Real defect classes that survive code review: off-by-one errors, async callbacks passed to forEach so the function returns before the work finishes, reference equality where value equality was meant, inverted cache expiry checks, a WHERE clause that silently converts a LEFT JOIN to an INNER JOIN, NOT IN against a nullable subquery, a defer registered before its error check, mutable default arguments, and sort comparators that return a boolean instead of a number.
How is the score calculated?
Your rank is based on how many of the four you got right, from Vibe Coder at zero to Principal AI Auditor at four. Speed contributes a smaller amount, so a correct careful answer always beats a fast wrong one. The percentile is a real comparison against every previous run, not an estimate — while the sample is still small it is labelled provisional rather than presented as a measurement.
Do I need an account?
No. There is no login, no payment, and no cookies. Grading happens on the server, so the answers are never sent to your browser.

Coming next: the full arena — multi-file codebases instead of isolated snippets, and a voice AI interviewer that pushes back on your reasoning. Take the benchmark to join the waitlist.