Vibe Code Bench
An end-to-end web application development benchmark (by Vals AI / Replit) where models build complete full-stack web apps from natural-language specifications in a sandboxed environment with production services (Supabase, Stripe, email), then are scored by an autonomous browser agent on overall application pass accuracy.
What this benchmark measures
An end-to-end web application development benchmark (by Vals AI / Replit) where models build complete full-stack web apps from natural-language specifications in a sandboxed environment with production services (Supabase, Stripe, email), then are scored by an autonomous browser agent on overall application pass accuracy.
Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.
The metric shown here is Overall accuracy. It should be interpreted within Vibe Code Bench, not compared as part of a site-wide ranking.
Frequently asked
What is Vibe Code Bench?
An end-to-end web application development benchmark (by Vals AI / Replit) where models build complete full-stack web apps from natural-language specifications in a sandboxed environment with production services (Supabase, Stripe, email), then are scored by an autonomous browser agent on overall application pass accuracy. It is a coding benchmark measured by Overall accuracy.
What does Overall accuracy mean on Vibe Code Bench?
Vibe Code Bench reports Overall accuracy (%); higher is better. Scores are shown only within Vibe Code Bench and are never averaged with other benchmarks.
What is the top reported Vibe Code Bench score?
Claude Opus 4.8 has the top reported score on Vibe Code Bench: 82.72% (Overall accuracy).
Why do Vibe Code Bench scores differ across runs?
Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.
Does evals.report rank models across benchmarks?
No. Vibe Code Bench scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".