Coding benchmark
Next.js Evals leaderboard
AI Agent Evaluations for Next.js. Every model the catalog carries a published Next.js Evals value for, ranked by that value.
CategoryCoding
MeasureAgent task completion with withheld Vitest assertions
Tasks24 Next.js code generation and migration tasks
DifficultyFramework-specific web application engineering
Published byAI Agent Evaluations | Next.js
A Vercel benchmark for AI coding agents on Next.js code generation and migration tasks, reporting success rate, average execution time, and an AGENTS.md documentation-assisted split.
No model in the catalog has a published Next.js Evals score.
The benchmark is defined by AI Agent Evaluations | Next.js, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.