VISTA: leaderboard
Metric: Structure-function score (0-1): mean over annotated interactions of reference localization times behavior correctness, agent builds and launches a multi-page web app from the product spec for 10 tasks (128 pages, 3,253 annotated interactions), mean over the five prompt-information conditions C0 to C4 (C1 averaged over its three stacks), Playwright-driven interaction evaluator; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 0.25 |
| 2 | GPT-5.5 | 0.22 |
Interactive version: theaggregate.ai/benchmark?slug=vista · How It Works · Data refreshed daily, snapshot 2026-10-07.