Meta 新模型在数字知识工作基准上缩小与 OpenAI 和 Google 差距
Meta 新模型第一次被评测机构认为能和 OpenAI、Google 掰手腕,这篇讲了基准对比细节。
Vals AI 创始人 Rayan Krishnan 评价 Meta 最新发布的模型在衡量数字知识工作的基准测试中表现接近 OpenAI 和 Google。他表示这是 Meta 第一次拿出具备前沿竞争力的模型。评语基于 Vals AI 对各家模型数字知识工作能力的基准评测结果。
Meta’s latest models are closing the gap with OpenAI and Google.
Vals AI Founder and CEO @RayanKrishnan explains how they stack up on benchmarks measuring digital knowledge work:
“I think this is really the first time that Meta's released models that are competing at the frontier.”