next-evals-oss

Evals for Next.js up to 15.5.6 to test AI model competency at Next.js

by vercel

Star on GitHub ForkWebsite npm

TypeScript

232 stars 32 forks 6 contributorsActive · 3d agoSince 2025

Meet the team

See all 6 on GitHub →

gaojude92 contributions

mclenhard22 contributions

Bot

vercel[bot]9 contributions

timneutkens2 contributions

Languages

View on GitHub →

TypeScript90%

JavaScript8.7%

CSS1.3%

Commit activity

Last 12 weeks · 104 commits

Full graph →

Community health

2 of 6 standards met

Community profile →

✓README✓License○Contributing○Code of Conduct○Issue Template○PR Template

Recent PRs & issues

Active · 10 in progress · Last activity 3d ago

See all on GitHub →

Testing remote docs perfOpenPR

Sonnet 4.6 scored 100% with local node_modules, but only 90% with remote docs.

gaojude · 3d ago

Recent fixes

View closed PRs →

Add Claude Sonnet 4.6 eval resultsMergedPR

Adds experiment configs and results for Claude Sonnet 4.6, both with and without AGENTS.md. Base pass rate is 70% (14/20). With AGENTS.md the pass rate jumps to 100% (20/20), a +30 point delta. The six evals that flipped from fail to pass with docs are , , , , , and . No regressions. The map and in are updated to include the new experiments.

gaojude · 5d ago

Structured data for AI agents

Repository: vercel/next-evals-oss. Description: Evals for Next.js up to 15.5.6 to test AI model competency at Next.js Stars: 232, Forks: 32. Primary language: TypeScript. Languages: TypeScript (90%), JavaScript (8.7%), CSS (1.3%). License: MIT. Homepage: https://nextjs.org/evals Open PRs: 10, open issues: 5. Last activity: 3d ago. Community health: 62%. Top contributors: gaojude, mclenhard, vercel[bot], timneutkens, quuu, elsigh.