Event ·Multi-source

Next.js 新一期评测：GPT-6 Sol 与 Opus 5.5 同达 97%

Vercel 发布新一期 Next.js 评测榜单，GPT-6 Sol 首次上榜即拿下 97% 成功率，与 Claude Opus 5.5、Claude Fable 5.1 并列第一。Grok 4.7 以 94% 排在第四，但价格便宜 2 到 7 倍。在三个 97% 模型中，Opus 5.5 的平均成本最低。完整榜单可在 nextjs.org/evals 查看。

Current read

Vercel 又更新 Next.js 评测了，GPT-6 Sol 首秀就并列第一，Grok 4.7 便宜一半到七倍，选模型前可以看看这份榜单。

11 sources58° AI heatLast updated 2026/9/22 22:03:10

Evidence

11 sources

Primary sourceGuillermo Rauch

2026/9/22 22:03:10View source

Related source 1shao__meng

2026/9/23 01:44:23View source

Related source 2Decoder

2026/9/21 16:56:36View source

Related source 3宝玉

2026/9/21 17:34:10View source

Related source 4eric zakariasson

2026/9/21 22:01:00View source

Related source 5lmarena.ai

2026/9/23 20:15:40View source

Related source 6OpenRouter

2026/9/21 16:31:16View source

Related source 7Cognition

2026/9/21 21:27:53View source

Related source 8Windsurf

2026/9/21 21:28:54View source

Related source 9AI Will

2026/9/22 01:18:18View source

Related source 10Aravind Srinivas

2026/9/22 19:06:52View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story