Skip to main content

AI Agent Evaluations for Next.js (Next.js Evals)

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.

How BenchLM shows Next.js Evals

BenchLM mirrors the public Next.js Evals agent leaderboard from Vercel. The source evaluates 18 model and coding-agent harness rows on 24 Next.js code generation and migration tasks, reporting base success rate, average duration, and a separate success rate when agents have bundled Next.js documentation through AGENTS.md.

Next.js Evals is display only on BenchLM. It is useful for framework-specific web development work, but each row combines a base model with a coding-agent harness such as Cursor, Claude Code, Codex, Gemini CLI, or OpenCode, so BenchLM keeps it out of weighted model-only rankings.

18 agent rows24 Next.js tasksCode generation and migrationAGENTS.md docs splitDisplay only

Success rate on Next.js Evals — June 1, 2026

BenchLM mirrors the published success rate view for Next.js Evals. Composer 2.5 leads the public snapshot at 92% , followed by Claude Opus 4.8 (88%) and GPT-5.5 Pro (83%). BenchLM does not use these results to rank models overall.

18 modelsCodingCurrentDisplay onlyUpdated June 1, 2026

The published Next.js Evals snapshot is tightly clustered at the top: Composer 2.5 sits at 92%, while the third row is only 9.0 points behind. The broader top-10 spread is 17.0 points, so the benchmark still separates strong models even when the leaders cluster.

18 models have been evaluated on Next.js Evals. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Next.js Evals is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Next.js Evals

Year

2026

Tasks

24 Next.js code generation and migration tasks

Format

Agent task completion with withheld Vitest assertions

Difficulty

Framework-specific web application engineering

Next.js Evals focuses on framework-specific web engineering tasks such as Pages Router to App Router migration, server actions, cache directives, proxy middleware, async cookies and headers, and other current Next.js patterns. BenchLM mirrors the public leaderboard as display-only because rows combine model choice with an agent harness.

BenchLM freshness & provenance

Version

Next.js Evals 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public tasks with withheld Vitest assertions

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Success rate table (18 models)

1
Composer 2.5Cursor Composer 2.5 / Cursor
92%
2
Claude Opus 4.8Claude Opus 4.8 / Claude Code
88%
3
GPT-5.5 ProGPT 5.5 Pro / Codex
83%
4
GPT-5.4GPT 5.4 (xhigh) / Codex
83%
5
GPT-5.3 CodexGPT 5.3 Codex (xhigh) / Codex
83%
6
MiniMax M3MiniMax M3 / OpenCode
75%
7
GLM-5.1GLM 5.1 / OpenCode
75%
8
Claude Opus 4.7 (Adaptive)Claude Opus 4.7 (max) / Claude Code
75%
9
Claude Opus 4.6Claude Opus 4.6 / Claude Code
75%
10
Composer 2Cursor Composer 2.0 / Cursor
75%
11
Gemini 3.1 ProGemini 3.1 Pro Preview / Gemini CLI
75%
12
Gemini 3.0 Pro PreviewGemini 3.0 Pro Preview / Gemini CLI
67%
13
Cursor Composer 1.5Cursor Composer 1.5 / Cursor
67%
14
Claude Sonnet 4.6Claude Sonnet 4.6 / Claude Code
58%
15
GPT-5.2-CodexGPT 5.2 Codex (xhigh) / Codex
58%
16
MiniMax M2.7MiniMax M2.7 / OpenCode
50%
17
Claude Sonnet 4.5Claude Sonnet 4.5 / Claude Code
50%
18
Kimi K2.5Kimi K2.5 / OpenCode
21%

FAQ

What does Next.js Evals measure?

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.

Which model leads the published Next.js Evals snapshot?

Composer 2.5 currently leads the published Next.js Evals snapshot with 92% success rate. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Next.js Evals?

18 AI models are included in BenchLM's mirrored Next.js Evals snapshot, based on the public leaderboard captured on June 1, 2026.

Last updated: June 1, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.