Magistral-Small-2506
Magistral-Small-2506 is an AI model published by MistralAI, released on 2025-06-10, for 推理大模型, with 240.0B parameters, and 128K tokens context length, under the Apache 2.0 license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Magistral-Small-2506 currently shows benchmark results led by AIME 2024 (39 / 62, score 70.68), LiveCodeBench (71 / 109, score 55.84), GPQA Diamond (109 / 166, score 68.18). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
2025年6月10日,巴黎——人工智能研究机构Mistral AI正式推出其首款推理专用大语言模型Magistral。该模型针对早期推理模型在专业深度、透明度及多语言一致性方面的局限设计,提供开源与企业双版本,支持复杂场景下的多步逻辑推演。
欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送
