Nace AI 发布金融决策模型 Drex for Finance
Nace AI has launched Drex for Finance, a model designed for split-second financial tasks, like determining whether a card payment looks fraudulent.
Nace AI 发布面向金融场景的多模态决策模型 Drex for Finance，用于欺诈判断等亚秒级金融决策，可结合文档或交易日志与固定候选答案输出每个答案的概率分数。在 48 个未参与训练的金融基准共 3361 个决策上，其准确率为 85.7%，GPT-6 Luna 为 70.9%。该模型仅在 Nace Console 提供。
查看原帖隆重推出 Drex for Finance——专为亚秒级金融决策进行后训练的多模态决策模型。 金融运营需要在申报文件、客服支持、信用风险、实时欺诈防范、量化信号与合规等环节做出精准、符合监管要求的决策，且不得出现任何幻觉。 在 48 个留出的金融基准上评估： - 在 3,361 项决策中准确率达 85.7%（较 GPT-6 Luna 提升 14.8%） - 金融指数 77.3（较 Jev 1.14 提升 13.7，较 Drex-Max v1.1 提升 11.5） 针对贯穿全流程的亚秒级金融智能进行训练： - 金融文档与申报文件：抽取决策、分类与聚类 - 信贷与借贷：自动化承保、PD 建模与 EWS - 欺诈与 AML：亚秒级交易评分、ATO 防御与 SAR 聚类 - 市场与交易：状态检测、元标注与 LOB 执行信号 - 保险科技与监管科技：理赔欺诈检测、制裁筛查与审计对账 仅在 Nace Console 独家提供：https://t.co/vdEavE1LhL
查看原文
Announcing Drex for Finance - the multimodal decision model, post-trained for sub-second financial decisions. Financial operations require precise, regulatory-grade decisions with zero hallucinations across filings, support, credit risk, live fraud prevention, quant signals, and compliance. Evaluated on 48 held-out finance benchmarks: - 85.7% accuracy across 3,361 decisions (+14.8% vs. GPT-6 Luna) - 77.3 Finance Index (+13.7 vs. Jev 1.14, +11.5 vs. Drex-Max v1.1) Trained for sub-second financial intelligence across the entire pipeline: - Financial Documents & Filings: Extraction decisions, classification, and clustering - Credit & Lending: Automated underwriting, PD modeling, and EWS - Fraud & AML: Sub-second transaction scoring, ATO defense, and SAR clustering - Markets & Trading: Regime detection, meta-labeling, and LOB execution signals - Insurtech & RegTech: Claims fraud detection, sanctions screening, and audit reconciliation Available exclusively on Nace Console: https://t.co/vdEavE1LhL
正文
Nace AI has launched Drex for Finance, a model designed for split-second financial tasks, like determining whether a card payment looks fraudulent.
It can use a document or a transaction log along with a fixed set of possible answers, then deliver a probability score for each one.
In tests with 3,361 decisions from 48 finance benchmarks not included in training, it was right 85.7% of the time, compared to 70.9% for GPT-6 Luna.