MODEL PROFILE · 模型档案

llama-3.1-medprm-reward-v1.0

dmis-lab · llama-3.1-medprm-reward-v1.0

🚀 Med-PRM-Reward is among the first Process Reward Models (PRMs) specifically designed for the medical domain. Unlike conventional PRMs, it enhances its verification capabilities by integrating clinical knowledge through retrieval-augmented generation (RAG). Med-PRM-Reward demonstrates exceptional performance in scaling-test-time computation, particularly outperforming majority‐voting ensembles on complex medical reasoning tasks. Moreover, its scalability is not limited to Llama-3.1-8B-Instruct: it delivers similarly outstanding results in scaling-test-time computation across multiple other medical‐specialized models. Notably, when combined with llama-3-meerkat-8b-v1.0, it became the first 8B model framework to surpass a score of 80 on the MedQA (4-option) benchmark. 📄 Paper: Med-PRM-Reward: Medical Reasoning Models with Stepwise, Guideline‑verified Process Rewards Across seven medical benchmarks, we conducted scaling‐test‐time computation using solutions generated by the Med-PRM-policy model, evaluating 64 solutions per question.

译文排队中,当前展示来源原文。

文本生成license:mit
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:15:43
OVERVIEW

模型介绍

🚀 Med-PRM-Reward is among the first Process Reward Models (PRMs) specifically designed for the medical domain. Unlike conventional PRMs, it enhances its verification capabilities by integrating clinical knowledge through retrieval-augmented generation (RAG). Med-PRM-Reward demonstrates exceptional performance in scaling-test-time computation, particularly outperforming majority‐voting ensembles on complex medical reasoning tasks. Moreover, its scalability is not limited to Llama-3.1-8B-Instruct: it delivers similarly outstanding results in scaling-test-time computation across multiple other medical‐specialized models. Notably, when combined with llama-3-meerkat-8b-v1.0, it became the first 8B model framework to surpass a score of 80 on the MedQA (4-option) benchmark. 📄 Paper: Med-PRM-Reward: Medical Reasoning Models with Stepwise, Guideline‑verified Process Rewards Across seven medical benchmarks, we conducted scaling‐test‐time computation using solutions generated by the Med-PRM-policy model, evaluating 64 solutions per question.

主要特点

特点摘要待依据来源补齐,不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价,不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价,请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

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。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用?

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗?

不是实时结算价格,而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

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。