ServiceActive

Nuxt AI Agent Evaluations

Benchmark results of AI coding agents on Nuxt code generation tasks, measuring success rate and execution time.

Open source page ↗

Field note

What it does

Performance results of AI coding agents on Nuxt code generation tasks, measuring success rate and execution time.

Capabilities

Available capabilities

Static site hostingBundlingServer-side rendering with data queriesRoute groupsReact Server ComponentsClient-side renderingRoutePage MetadataHybrid RenderingSide Effects TriggeringClient-side navigationServer-side RenderingNuxt Kit ModulesCollapsible sectionsRendering and GraphicsClient-Side RenderingServer-Side RenderingRules for relevance overrideUniversal RenderingServer Engine

Tags

Tags

NuxtAI AgentsAI BenchmarkAIBenchmarkEvaluation

Ways to use it

Ways to use it

No integrations filed yet.

Product features

Product features

Avg Duration

Mean time an agent took per eval.

Avg Duration

Mean time an agent took per eval.

Avg List Cost

Mean cost per eval estimated from tokens used at public list price.

Avg List Cost

Mean cost per eval estimated from tokens at provider public list price.

Client-Side Rendering

Deploying a Static Client-Rendered App

Edge-Side Rendering

First-Try Rate

Percentage that passed on the first attempt, used to break ties.

First-Try Rate

Percentage that passed on the first attempt, used to break ties.

Hybrid Rendering

Per-Eval Results

Expandable rows showing per-eval results with attempt badges.

Rendering Modes

Route Rules

Server Bundle Size with ssr: false

Server-rendering the Error Page

Skipping Client Fallback Generation

Success Rate

Percentage of evals that passed on at least one attempt.

Success Rate

Percentage of evals that passed on at least one attempt, up to 4 attempts.

Universal Rendering

What are 200.html and 404.html?