决策模型这个赛道里 Drex Max v1.1 拿了 72.6 分排第一,价格还比 Jev 1.14、Claude Haiku 5.5 这些对手便宜。做文档抽取和流程决策的团队可以直接在 console.nace.ai 试试 API,开源版也能自己部署。
#Nace AI
做预测市场或概率判断类的开发者可以看看这套架构:Drex 自己打分,低于90%置信度才调 Claude 复核,108条全对还比纯用 Claude 便宜93%。分层调用的省钱思路很实用。
Nace AI 推出的 Drex 能直接修复歪斜、模糊的扫描文档照片,官方测试显示比整页重新生成快 38%,每千页 7 美元,支持 PDF、表格、邮件等 30 种格式。经常处理扫描件和拍照文件的团队可以对比一下现有 OCR 方案的成本和速度。
Nace AI 把决策模型这个细分赛道做出了第一名,73 分登顶 Artificial Analysis Decision Index,还能在 Mac 上本地跑。想找低延迟、能跨图像视频做判断的模型的开发者可以先去试用页体验一下。
Nace AI 新出的 Drex Max 1.1 专管智能体选下一步动作,屏幕内容也能看。Artificial Analysis 上 73 分追平对手,价格只要对方八分之一,跑智能体工作流的人可以拿它降成本试试。
Nace AI 把 Drex Max v1.1 做到了 Decision Index 第一名,速度快还能处理多模态输入。做智能体或研究工作流的朋友可以直接调 API,有约 100 万次免费额度,开源权重也快放了,想在本地跑决策模型的可以关注。
Calibration training—tuning confidence to match real accuracy—is the detail that separates this from typical fine-tuning writeups, since miscalibrated probabilities are a common failure point for models used in decision support. Practitioners evaluating open-weight models for document-heavy workflows can compare Drex's approach against closed APIs and test it directly in Nace Console. The full training methodology is public, making it a useful reference for teams building constrained-answer systems.
Routing thousands of micro-decisions to a pick-only model could cut agent orchestration costs by orders of magnitude where the answer space is a finite option list, not free text. Builders running multi-step agent pipelines can plug it in as a cheap decision layer while keeping a general model for generation. The gap on HLE shows it is a narrow tool, not a replacement for reasoning models.
Nace AI 开源了决策模型 Drex,权重代码都放出来了,Drex Max 在几个决策基准上能跟 GPT-6 Sol 掰手腕,想本地部署可以试试。
The interesting part is the interface shift: instead of generating text, these models emit calibrated probabilities over fixed options, which suits scoring, routing and agentic decision points where latency matters. Builders assembling agent pipelines or classification backends can try the weights on Hugging Face or read the paper at arxiv.org/abs/2611.07854. Compared with calling Claude Opus 5.5 or GPT-6 Sol, Drex trades text generation for sub-200ms structured decisions under an open licence.
Nace AI 在搞 120% 返现,改 3 个环境变量就能换到 Drex Max,跑 agent 任务只要 Claude Code 约 1/10 的钱。
Nace AI 出了个金融专用模型 Drex,专门做欺诈判断这种毫秒级任务,48 个金融基准测试准确率 85.7%,比 GPT-6 Luna 的 70.9% 高不少。
Nace AI 开源了决策模型 Drex Max,一台 M4 或 M5 Mac 就能跑,输入文档和选项就能输出各答案概率,做工单分流这类判断任务挺实用。
Nace AI 开源了 27B 的 Drex Max v1 决策模型,Mac 上就能本地跑,权重直接可下载。
A 94.7% score on MADQA positions Drex for Search as a serious retrieval option for agents that must cite exact pages from enterprise documents. Its availability as an MCP tool means teams already running Claude Code, Codex, Cursor or OpenCode can plug it in without changing their stack. Developers building document-grounded agents should benchmark it against their current RAG setup.
Nace AI 把 Drex 决策模型用到智能体搜索上了,BrowseComp-Plus 跑到 92.05%,而且平均只用 12.6 次搜索调用,做搜索智能体的可以看看。
The gains come from cutting agent steps and input tokens by more than half, which lowers API costs on retrieval-heavy workloads rather than just raising accuracy a few points. Teams building agents over enterprise document stores can plug it into Claude Code, Codex or Hermes Agent as a tool. The OfficeQA benchmark result offers a direct comparison point for evaluating retrieval layers before committing to one.
Nace AI 新出的 Drex Max 专给计算机操作智能体做决策,能看截图输出校准概率,Decision Index 拿了 67.59 分。
Nace AI 的 Drex Max 正在早期测试阶段,想尝鲜的可以直接去 console.nace.ai 试试,详细测评文章后面会出。
A decision model tuned for reading screens first could simplify computer-use and browser-use agents, where each step currently depends on interpreting the display before acting. Developers building such agents can evaluate it against Jev 1.14 on Mind2Web and the Decision Index. At US$0.06 per 1M input tokens, pricing is a concrete comparison point for teams balancing latency and cost.
Nace AI 出了个专门做选择题的决策模型 Drex Max,能看截图给每个选项打分,比 Claude、GPT 这些模型便宜最多 167 倍,做浏览器智能体的可以试试。
The 128k context window eliminates preprocessing for long documents, a significant advantage over previous decision models. Developers can now handle entire legal or video analysis tasks in a single pass, with a cost-effective option at $0.04 per 1M tokens. This model's top ranking on the Decision Index makes it a compelling alternative for businesses needing automated decision systems.