Model overview
**LegalOne** 是一系列专门为中文法律领域训练的LLM，采用**多阶段训练框架**来联合增强法律知识和推理能力。模型基于 **昇腾 Atlas 910B** 计算平台与 **昇思 MindSpore** AI 框架完成训练。 **LegalOne-8B** 在**法规解释、判例法推理、法律问答、文档起草**等任务上超越通用 LLM 和现有法律模型。在 **LexEval、JecQA** 等权威评测中，整体性能可媲美更大参数规模的通用模型（如 **DeepSeek-R1、Qwen3-Max**），并在部分任务上实现超越。尤其在**法律概念理解、法条记忆、多跳推理**等关键任务上，**LegalOne-8B** 达到了当前开源模型的**领先水平**。 基于高质量法律文书，通过智能体 CoT 蒸馏管道，我们合成了涵盖法律咨询、判决预测、法律摘要、法律适用、文书生成等多种经典司法场景的数据。结合部分开源的通用指令遵循数据以保持模型的通用能力，最终获得 **500k** 高质量监督微调数据。
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：mit。模型介绍与第三方评测均以原来源的具体版本和方法为准。