Ant Digital Technologies Releases Decision Model LingDT-Decision-1.0, Cutting Token Consumption by Over 90%

Ant Digital Technologies Releases Decision Model LingDT-Decision-1.0, Cutting Token Consumption by Over 90%

2026-10-22 18:12 IT Home - Haomiao

Thanks to IT Home user Cactus for the tip submission!

IT Home, October 22 news: Ant Digital Technologies today released the decision model LingDT-Decision-1.0. This model is purpose-built for rapid industrial decision-making and, when handling structured decision tasks, offers advantages including higher accuracy, faster responses, and lower Token costs.

According to the introduction, compared with other decision models, LingDT-Decision-1.0 is the first to support native multi-select and ordered decision-making capabilities, better adapting to real enterprise application scenarios. Across 23 open-source evaluation benchmarks, LingDT-Decision-1.0 outperformed popular decision models such as Microsoft-Decision-1 and Jev 1.13, and the 27B version of LingDT-Decision-1.0 achieved the highest accuracy among models with the same parameter count.

Tests by the Ant Digital Technologies team in real business scenarios such as customer service, risk control, and finance show that when handling the same tasks, LingDT-Decision-1.0 can reduce Token consumption by over 90% compared with large language models, improve response time by 10x, and deliver better performance.

In actual enterprise applications, there are a large number of high-frequency decision-type tasks. For example, in a customer service scenario, after receiving the inquiry "This order has been three days and still hasn't shipped, please handle it as soon as possible," AI needs to quickly make a series of judgments and decisions: the problem type (refund, expedite request, or complaint?), ticket urgency (whether priority handling is needed), assigned department (which department the ticket goes to), and risk judgment (whether manual takeover is needed).

Traditional large language models have obvious shortcomings in such scenarios. Large language models usually need to reason token by token and then generate output text, resulting in a long chain, high cost, greater susceptibility to errors, and insufficiently stable performance. Decision models are designed precisely for these pain points; their goal is not to generate text but to make fast, accurate judgments. Therefore, they are naturally suited to undertaking high-frequency decision-type tasks in enterprise business, such as intent judgment, tool selection, rule classification, and result scoring.

Compared with other decision models, Ant Digital Technologies' LingDT-Decision-1.0 places greater emphasis on being built for real enterprise application scenarios. In addition to basic capabilities such as judgment, single-choice, classification, and rating, LingDT-Decision-1.0 also debuts native multi-select and ordered decision-making (DAG) functions, which can better adapt to complex, multi-step decision-making needs in enterprise business.

LingDT-Decision-1.0 is available in two versions, 4B and 27B. The model is currently live on the Ant Digital Technologies DTMaaS platform. Developers can try it free for a limited time.