Next.js coding
Next.js Evals
Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better.
Rankings
Higher is better192%
Composer 2.5
Cursor · May 18 2026
192%
Claude Fable 5
Anthropic · Jun 9 2026
388%
Claude Opus 4.8
Anthropic · May 28 2026
388%
GLM-5.2
Z.ai · Jun 16 2026
583%
GPT-5.3-Codex
OpenAI · Feb 5 2026
583%
GPT-5.4
OpenAI · Mar 5 2026
583%
GPT-5.5-Pro
OpenAI · Apr 23 2026
875%
Claude Opus 4.6
Anthropic · Feb 5 2026
875%
Gemini 3.1 Pro
Google · Feb 19 2026
875%
Composer 2
Cursor · Mar 20 2026
875%
GLM-5.1
Z.ai · Apr 7 2026
875%
Claude Opus 4.7
Anthropic · Apr 16 2026
875%
Kimi K2.7 Code
Moonshot AI · Jun 12 2026
1467%
Gemini 3.0 Pro
Google · Nov 18 2025
1467%
Composer 1.5
Cursor · Feb 8 2026
1467%
Kimi K2.6
Moonshot AI · Apr 21 2026
1758%
Claude Sonnet 4.6
Anthropic · Feb 17 2026
1850%
Claude Sonnet 4.5
Anthropic · Sep 29 2025
1921%
Kimi K2.5
Moonshot AI · Jan 27 2026