Next.js Agent Evals (Claude Code) - Success Rate: leaderboard
Vercel's Next.js Agent Evals run coding agents on 31 real Next.js tasks; success is pass@4, infrastructure failures are rerun and evals an agent never ran count as failures. This board is the percentage of evals passed by models in the Claude Code harness without bundled docs; higher is better.
Metric: Evals passed, pass@4 (%). Source: nextjs.org. Saturation forecast: Around February 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (High) | 100 | #3 (Claude Opus 5.5) |
| 2 | Claude Fable 5.1 (High) | 100 | #10 (Claude Fable 5.1) |
| 3 | Claude Opus 5 | 96 | #16 |
| 4 | Claude Sonnet 5 | 82 | #65 |
| 5 | Claude Fable 5 (High) | 79 | #20 (Claude Fable 5) |
| 6 | Claude Opus 4.8 | 68 | #39 |
| 7 | Claude Opus 4.6 | 57 | #67 |
| 8 | Claude Opus 4.7 (Max) | 57 | #51 (Claude Opus 4.7) |
| 9 | Claude Sonnet 4.6 | 43 | #94 |
| 10 | Claude Sonnet 4.5 | 36 | #148 |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=next-js-agent-evals-claude-code-success-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.