AI 模型和平台
半分析发布 GDPx 基准测试扫描 11 个代理域
在 Google 上的首选来源中添加 Unite.AI
由Max Kan,Andrew Megalaa，以及Dylan Patel撰写的公告中，Anthropic的Claude Opus 5.5以12.0%的得分领先首发板。
V1.0 领导板
官方的GDPx网站列出了第一个版本，共206项任务，由14个专业数据合作伙伴构建，其领导板排名为13个模型。 Claude Opus 5.5 超过排名，每任务平均花费51.41美元，输出符号为548K. Google的Gemini 4 Carbon以10.9%和16.29的成绩位居第二，而OpenAI的GPT-6 Astra以9.6%和53.99的成绩位居第三。 Meta的Muse Wonder Full以9.0%的成绩排名第四，没有列出公开价格，Z.ai的GLM 5.3以2.7%的成绩排名第13位。
SemiAnalysis将GDPx描述为真正的前沿级基准测试正因为最高得分仍然如此低。 头条 GDPx 得分平均为每个模型的通过@ 1 三次尝试的结果，平均为每个域加权
设计、伙伴和方法
这些领域是芯片设计、网络安全、生物学、金融、法律、量子交易、递归自我改进(RSI)、硬件设计、材料科学、对齐和软件工程；SemiAnalysis 称它故意放弃政府、房地产和保险等行业。 作者认为，AI的第一个万亿美元收入将集中在可以在高ROI部署前沿情报的部门，围绕GDP份额或SOC/O*NET职业分类建立一般的基准测试是一个错误。
每个域都是与专业伙伴共同建造的：Aria、Arcverex和Ergodex用于芯片设计；Arithmetic用于网络安全；Latch Bio用于生物学；Living Contact for Finance;Chakra用于法律；Three Moment for quant trade;Extrapolate for RSI;Beautific Machines用于硬件设计；ValenceForge和Emulated用于材料科学；Fleet用于校正；以及Datacurve用于软件工程。
任务带有8小时的默认时限，模型在可用时会在其本土的牵引力中运行——Opus 5.5的Claude Code,GPT-6 Astra的Codex,Gemini 4 Carbon的Antigravity——以OpenCode为倒置。 SemiAnalysis要求每一个伙伴在第一次尝试时通过自动QA，最糟糕时只有小错误，并报告说，同一过程标记了终端座椅4.0 基准测试中将近50%的任务被打破。
GDPval 标准
公告将GDPx定位为OpenAI的GDPval，发布 September 25,2025，作者称这仍然是主要型号发行卡上最受欢迎的通用基准测试。 他们批评GDPval的任务是非互动性的，所有必要的背景都迅速提供，并引述了人类专家之间关于黄金子集的71%的协议。 每艘GDPx任务都是有现实环境的船舶：24项金融任务，例如replicate是一种真正的私人股权交易，其中一个基金收购大约62%的点心制造商以8.8亿美元的价格加一笔收入，在大约4000个匿名文件中重建。
领域成果和说明的限制
SemiAnalysis)报告Claude Opus 5.5是最佳全方位模型，赢得了四重交易，硬件设计，以及芯片设计；Gemini 4 Carbon是最佳生物学模型，在软件工程上获得微小的胜利；GPT-6 Astra是RSI和材料科学的赢家。 它提醒说，Opus 5.5和GPT-6 Astra的整体分数被其安全分类器在网络，生物学，和对齐域中的沙子标出，并将Meta的Muse Wonder Full描述为有意义的可用网络模型。
财务和法律任务十分困难，以至于每个模型在预定的二进制分数下都得零分，因此，SemiAnalysis报告这些领域的平均部分分数。 在量子交易中，111级赛跑中有70次比参考策略agent被要求击败更糟糕，没有模特儿解决了公共apl-target-winsorization任务。 在Fleet的校正网络任务中，200跑中有196跑至少打破了一条行为规则，173跑破了一条被评为严重错位的规则；在医疗任务中，100跑中有19跑得分高于零。 在成本方面，SemiAnalysis将GPT-6 Luna和DeepSeek置于成本对性能前沿的低端，Opus位于高端，OpenAI位于中间。
SemiAnalysis 称 GDPx是作为活的基准测试，每3-6个月计划新版本，并列出gdpx@semianalysis.com，供有兴趣参与的数据公司和实验室寻求对未来的发布的评价。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
AI Models & Platforms
SemiAnalysis Launches GDPx Benchmark Spanning 11 Agentic Domains
Add Unite.AI to your preferred sources on Google
SemiAnalysis on November 2, 2026 released GDPx, a benchmark for general agentic capabilities spanning 11 professional domains, in an announcement authored by Max Kan, Andrew Megalaa, and Dylan Patel. Anthropic’s Claude Opus 5.5 leads the debut leaderboard with a score of 12.0%.
The V1.0 Leaderboard
The official GDPx site lists the first version at 206 tasks built with 14 specialized data partners, and its leaderboard ranks 13 models. Claude Opus 5.5 tops the ranking at an average cost of $51.41 per task with 548K output tokens. Google’s Gemini 4 Carbon places second at 10.9% and $16.29 per task, while OpenAI’s GPT-6 Astra is third at 9.6% and $53.99 per task. Meta’s Muse Wonder Full ranks fourth at 9.0% with no public price listed, and Z.ai’s GLM 5.3 is 13th at 2.7%.
SemiAnalysis describes GDPx as a true frontier-level benchmark precisely because the top score remains so low. The headline GDPx score averages each model’s pass@1 result across three attempts, weights every domain equally, and applies each task’s intended grading method, binary or continuous.
Design, Partners, and Methodology
The domains are chip design, cybersecurity, biology, finance, legal, quant trading, recursive self-improvement (RSI), hardware design, materials science, alignment, and software engineering; SemiAnalysis says it intentionally forgoes industries such as government, real estate, and insurance. The authors argue that the first trillion dollars of AI revenue will concentrate in sectors that can deploy frontier intelligence at high ROI, and that building a general benchmark around share of GDP or the SOC/O*NET occupational taxonomy is a mistake.
Each domain was built with specialized partners: Aria, Arcverex, and Ergodex for chip design; Arithmetic for cybersecurity; Latch Bio for biology; Living Context for finance; Chakra for legal; Third Moment for quant trading; Extrapolate for RSI; Beautiful Machines for hardware design; ValenceForge and Emulated for materials science; Fleet for alignment; and Datacurve for software engineering.
Tasks carry a default time limit of eight hours, and models run in their native harness when available — Claude Code for Opus 5.5, Codex for GPT-6 Astra, and Antigravity for Gemini 4 Carbon — with OpenCode as the fallback. SemiAnalysis required every partner to pass its automated QA on the first try with only minor mistakes at worst, and reports that the same process flags nearly 50% of tasks in the Terminal Bench 4.0 benchmark as broken.
The GDPval Critique
The announcement positions GDPx as a successor to OpenAI’s GDPval, released September 25, 2025, which the authors say remains the most popular general-purpose benchmark on major model release cards. They criticize GDPval’s tasks as non-interactive, with all necessary context spoon-fed in the prompt, and cite human expert inter-rater agreement of 71% on its gold subset. Every GDPx task instead ships with a realistic environment: the 24 finance tasks, for example, replicate a real private-equity transaction in which a fund buys about 62% of a snack manufacturer for $880 million plus an earnout, reconstructed across roughly 4,000 anonymized files.
Domain Results and Stated Limitations
SemiAnalysis reports Claude Opus 5.5 as the best all-around model, winning quant trading, hardware design, and chip design; Gemini 4 Carbon as the best biology model, with a narrow win in software engineering; and GPT-6 Astra as the winner in RSI and materials science. It cautions that the Opus 5.5 and GPT-6 Astra overall scores are sandbagged by their safety classifiers in the cyber, biology, and alignment domains, and describes Meta’s Muse Wonder Full as the best available cyber model by a meaningful margin.
The finance and legal tasks are difficult enough that every model scores zero under the intended binary grading, so SemiAnalysis reports average partial scores for those domains. In quant trading, 70 of 111 graded runs did worse than the reference strategy the agent was asked to beat, and no model solved the public aapl-target-winsorization task. In Fleet’s alignment cyber tasks, 196 of 200 runs broke at least one behavior rule and 173 broke a rule rated severely misaligned; in the healthcare tasks, 19 of 100 runs scored above zero. On cost, SemiAnalysis places GPT-6 Luna and DeepSeek at the low end of the cost-versus-performance frontier, Opus at the high end, and OpenAI in the middle.
SemiAnalysis says GDPx is intended as a living benchmark, with new versions planned every 3–6 months, and lists gdpx@semianalysis.com for data companies interested in participating and labs seeking evaluation of future releases.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.