SemiAnalysis 发布 GDPx 基准，测试智能体在 11 个领域的专家工作
SemiAnalysis has released GDPx, a benchmark testing AI agents on expert work across 11 domains.
SemiAnalysis 发布 GDPx 基准，用 11 个领域的专家任务测试 AI 智能体，最高分的 Claude Opus 5.5 平均仅 12%，Gemini 4 Carbon 以 10.9% 次之。任务涵盖芯片设计、网络安全、金融和法律等，来自 14 家专业数据合作方；与在提示词中直接给上下文的 OpenAI GDPval 不同，GDPx 要求智能体在类似 3,983 份文件构成的真实收购案副本等工作区中自行查找。金融和法律任务上所有模型在通过制评分下均为 0 分，因此改用部分给分；在改进现有交易策略的 111 次尝试中，有 70 次模型表现不如原策略，往往只是加大风险。
正文
SemiAnalysis has released GDPx, a benchmark testing AI agents on expert work across 11 domains.
The top model, Anthropic’s Claude Opus 5.5, averages just 12%, with Google’s Gemini 4 Carbon next at 10.9%.
OpenAI’s GPT-6 Astra tops AI-research and materials-science tasks.
The tasks, spanning chip design, cybersecurity, finance and law among others, come from 14 specialized data partners.
Unlike OpenAI’s GDPval, which feeds models context in the prompt, GDPx makes agents dig through workspaces such as a 3,983-file replica of a real acquisition.
Excluding cyber, biology and alignment, where safety classifiers sometimes intervene, lifts OpenAI’s GPT-6 Astra from 9.6% to 11.8%, past Opus.
Finance and law defeat every model: all score 0 under pass-fail grading, so GDPx reports partial credit instead.
Asked to improve a working trading strategy, models did worse than the original in 70 of 111 attempts, often just taking bigger risks instead of finding better trades.