Speed-to-first-paint across AI app builders (June 2026)

Speed is the metric people feel before they can articulate it. A builder that shows a working preview in ten seconds feels categorically different from one that takes a minute, even when the slower tool produces better code. This protocol separates the feeling into two measurable clocks.¹

Background

"Fast" is ambiguous. There is the speed at which a builder shows you something, a first paint that tells you it understood the prompt, and the speed at which it gives you something you can actually ship. These are different quantities, and conflating them produces misleading leaderboards.²

So the protocol measures both. Speed-to-first-paint rewards responsiveness and is what most demos implicitly show off. Time-to-working-app rewards getting to a correct, runnable result and is what actually governs how much of your afternoon a builder consumes. The two often disagree, and the disagreement is the interesting part.³

The protocol

Each builder runs the same lightweight brief, a two-page app with one form and one list view, five times from a cold session, on a fixed network profile, with no warm cache.

The protocol times the production-equivalent path, not a cached or pre-warmed demo state. Cold runs are harsher and noisier, but they reflect the experience of actually starting a new project rather than re-rendering one the platform already has in memory.⁴

Results

What still holds without the numbers

Two points survive the withdrawal, because they are properties of the measurement design rather than results.

The two clocks can rank a field differently. A builder that paints early is not necessarily the one that reaches a passing app first, and a single blended "speed" score hides exactly that. If your workflow is "show a client something in the meeting", first paint matters most. If it is "get to a deployable result", the second clock is the one to watch.⁵

Spread is a result, not noise to be averaged away. A wide min to max range is a usability cost even when the median looks fine, because the slow runs are the ones you remember. Any speed benchmark that publishes a median without a spread is withholding half the finding.⁶

Caveats

Absolute seconds are environment-bound in any case. Network profile, region and test timing differ between any two operators, and provider load varies through the day, so a builder under heavy load during its window can look worse than it usually is.⁸

The brief is intentionally small, to isolate startup latency from generation volume. A larger brief widens every number and can reorder the field, because builders that stream output incrementally feel faster on big tasks than their first-paint number suggests. "Manual edits to pass" is a blunt instrument, since one trivial edit and one substantial edit both count as edits, so it is read alongside the time figure rather than instead of it.

Speed is among the most volatile things this lab tracks, because it moves with model and infrastructure changes that ship without notice. Any future timing carries a run date and is read against that date.

Publication date correction, August 24, 2026

A date audit run on August 24, 2026 found that the publication timestamp stored for this page predated the registration of builderproof.org, so the recorded date cannot be the date on which this page was published. The stamp was an artifact of the launch content import rather than a real publication date, and no publication log survives that would let the true one be recovered. The timestamp has been corrected to the earliest date consistent with the evidence that does survive. The benchmark text, the protocol and the August 21, 2026 withdrawal notice at the top of this page are unchanged.

BuilderProof editorial team. "Speed-to-first-paint across AI app builders (June 2026)". BuilderProof, June 2026. https://www.builderproof.org/benchmarks/speed-to-first-paint-ai-app-builders-june-2026.

@misc{builderproof-speed-to-first-paint-ai-app-builders-june-2026,
  title  = {{Speed-to-first-paint across AI app builders (June 2026)}},
  author = {{BuilderProof editorial team}},
  year   = {2026},
  month  = {jun},
  howpublished = {\url{https://www.builderproof.org/benchmarks/speed-to-first-paint-ai-app-builders-june-2026}},
  note   = {BuilderProof, builderproof.org}
}