MiniMax 发布 M2.7 模型，SWE-Pro 得分 56.22%
MiniMax M2.7: Early Echoes of Self-Evolution - MiniMax Research | MiniMax
MiniMax 发布 M2.7，官方称其在真实软件工程任务中表现突出，SWE-Pro 得分 56.22%，接近 Opus 的最佳水平，VIBE-Pro 为 55.6%，Terminal Bench 2 为 57.0%。在专业办公软件领域，M2.7 的 GDPval-AA ELO 得分为 1495，为开源模型中最高，并提升了 Excel、PPT、Word 的复杂编辑与多轮修订能力。该模型在与 40 多个、每个超过 2000 tokens 的复杂技能协作时保持 97% 的技能遵循率，官方还展示了用于模型自进化的 agent、多智能体协作演示及 WildGuard 网页生成案例。
推荐理由
AI 评分 69
MiniMax 官方公布 M2.7 在 SWE-Pro、Terminal Bench 2 等基准上的成绩，可对照其与 Opus 及开源模型的差距。
主题
正文
当前显示原文，中文全文译文尚未就绪。
M2.7 delivers outstanding performance in real-world software engineering, including end-to-end full project delivery, log analysis, bug troubleshooting, code security, machine learning, and more. On the SWE-Pro benchmark, M2.7 scored 56.22%, nearly approaching Opus's best level. This capability also extends to end-to-end full project delivery scenarios (VIBE-Pro 55.6%) and deep understanding of complex engineering systems on Terminal Bench 2 (57.0%); We have also enhanced the model's expertise and task delivery capabilities across various fields in the professional office software domain. Its ELO score on GDPval-AA is 1495, the highest among open-source models. M2.7 shows significantly improved ability for complex editing in the Office suite — Excel, PPT, and Word — and can better handle multi-round revisions and high-fidelity editing. M2.7 is capable of interacting with complex environments: It maintains a 97% skill adherence rate while working with over 40 complex skills, each exceeding 2,000 tokens; M2.7 exhibits excellent character consistency and emotional intelligence, opening up more room for product innovation
Building an agent for model self-evolution
Professional Software Engineering
Live production environment debugging
WildGuard demo webpage generated by M2.7
Agent Teams multi-agent collaboration demo
Professional Work
Entertainment