Stubbi
Rankings
Benchmark

Next.js Agent Evals

Test coding agents on practical Next.js development tasks, with and without bundled-documentation guidance.

Checked Nov 18, 2026Official Next.js evaluation

Explore the original evidence

Explore the original evaluation, its methods, and reported findings.

Open eval

Coverage

Next.js application tasks evaluated across model and agent combinations. Current and superseded results are separate; changed tasks can retain older measurements until rerun.

Methodology

An agent modifies an app in an isolated sandbox, then withheld assertions check its work. The public leaderboard uses pass@4: a task passes if any of four attempts passes. Both conditions can access bundled documentation; AGENTS.md adds initial guidance. Infrastructure failures are rerun. Release automation can use a separate pass@1 protocol.

People & organizations

1

Sources

Original evaluation repository and protocolHN discovery comment