Perplexity CEO 分享 Gemini 4 Carbon 早期评测：WANDR 基准刷新 SoTA
Sharing early evals on Gemini 4 Carbon. Strongest model that we've seen so far for long-form research and answer quality, with a new SoTA on the Wide-And-Deep-R
AI 导读
Perplexity CEO Aravind Srinivas 分享 Gemini 4 Carbon 的早期评测，称其是目前在长文研究和回答质量上最强的模型，并在 Wide-And-Deep-Research（WANDR）基准上取得新的 SoTA。该模型将在 token 容量充足后向所有 Perplexity Pro 和 Max 用户开放，集成在 Computer 中。
推荐理由
AI 评分 55
Perplexity CEO 给出 Gemini 4 Carbon 的早期实测，并提到它在长文研究基准上刷新 SoTA。
主题
正文
Sharing early evals on Gemini 4 Carbon. Strongest model that we've seen so far for long-form research and answer quality, with a new SoTA on the Wide-And-Deep-Research (WANDR) benchmark. Coming soon to all Perplexity Pro and Max users inside Computer, once we have sufficient token capacity. Congrats @GoogleDeepMind!