AITOPAI热报
Papers

研究：Claude Opus 4.8 在同行评审中表现匹敌人类专家

Ethan Mollick@emollick
Post
View the post
Why we picked it

有人拿 124 篇哈佛论文测试 Opus 4.8 当审稿人，结果和人类专家打平，搞科研的朋友可以看看细节。

一项研究用 124 篇哈佛社会科学论文测试 Claude Opus 4.8 的同行评审能力，覆盖统计分析、形式化模型和定性研究等多种类型。结果显示 Opus 4.8 在各项指标上都达到人类专家评审员的水平。Ethan Mollick 转发了这项研究，并指出学术界需要尽快调整科研实践来适应 AI。

Original · Ethan Mollick

By every measure, Opus 4.8 beats human experts as peer reviewers in a study of 124 Harvard social science papers covering a range from statistical analyses to formal models to qualitative work.

As academics, we need to figure out how to adapt the practice of science to AI, fast. https://t.co/a9Q1pMd6E6

#Claude#Opus 4.8#同行评审#科研#Anthropic

Keep reading

Recent stories with the same tag or section
ModelsUS vs ChinaSelected06:51
AA-PersonalityBench links model slop to intelligence gaps

Slop output is only loosely tied to raw capability, so model selection for writing or content pipelines should weigh the Slop ranking separately from the Intelligence Index. Teams building customer-facing copy or summarisation tools can use these two scores as a joint filter instead of assuming a smarter model reads better. Qwen3.8 Max ranking high on both lists is a useful data point when weighing it against Gemini 4 Argon or GPT-6 variants.

#GPT-6#Qwen3.8 Max#Claude#Gemini
官方账号Artificial Analysis@ArtificialAnlysSource