Unlocking the Reasoning Potential of Language Model From Pretraining to Posttraining MATH500 (Pass@1) 95.8 97.2 AIME 2024 (Pass@1) 68.2 80.1 AIME 2025 (Pass@1) 55.4 70.2 Code LiveCodeBench v5 (Pass@1) 57.8 60.9 LiveCodeBench v6 (Pass@1) 49.3 52.2 STEM GPQA-Diamond (Pass@1) 54.4 60.6 General Alignbench1.1 (Evaluated by GPT4.1) 6.9 7.4 Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities. Moreover, it was widely considered that achieving uniform and simultaneous improvements in both mathematical and code capabilities within a small model is challenging. Nonetheless, we believe that the effectiveness of the RL trained reasoning model relies on the inherent reasoning potential of the base model. To fully unlock the reasoning potential of language models, efforts must focus not only on post-training but also on pre-training strategies tailored to reasoning.
Unlocking the Reasoning Potential of Language Model From Pretraining to Posttraining MATH500 (Pass@1) 95.8 97.2 AIME 2024 (Pass@1) 68.2 80.1 AIME 2025 (Pass@1) 55.4 70.2 Code LiveCodeBench v5 (Pass@1) 57.8 60.9 LiveCodeBench v6 (Pass@1) 49.3 52.2 STEM GPQA-Diamond (Pass@1) 54.4 60.6 General Alignbench1.1 (Evaluated by GPT4.1) 6.9 7.4 Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities. Moreover, it was widely considered that achieving uniform and simultaneous improvements in both mathematical and code capabilities within a small model is challenging. Nonetheless, we believe that the effectiveness of the RL trained reasoning model relies on the inherent reasoning potential of the base model. To fully unlock the reasoning potential of language models, efforts must focus not only on post-training but also on pre-training strategies tailored to reasoning.
MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity. We release this SFT checkpoint as a starting point for open research in agentic reinforcement learning. Results for the released SFT checkpoint, as reported in the MiMo-V2.6 technical report. The weighted SFT data mixture contains 77.4B total tokens, including 27.2B loss-bearing tokens.
> [!IMPORTANT] > **This is the MOPD upgrade of the MiMo-V2.6-Flash-RL checkpoint.** > > - **MOPD2** (👉 **Technical Report §5.6**) > Fuses several domain-specialized teachers into one model, extending to domains where reliable training-time verification is hard, such as long-horizon game development, scientific research and embodied intelligence. > - **Diagnosing and Mitigating Tool-Call Repetition in MiMo-V2.6** (👉 **Technical Blog**) > An easy-to-overlook failure mode in which the model keeps issuing the same or highly similar tool calls, appearing busy while making no progress. Nothing fails outright, so it tends to go unnoticed. The MOPD stage handles it efficiently, with a short specialized-teacher run that converges quickly. MOPD2 distills several domain-specialized teachers into the student on-policy. The teachers fall into two families: **mixRL teachers**, trained on verifiable tasks, and **SFT teachers**, trained on synthetic demonstrations for open-domain tasks where a reliable reward is hard to design. Three streams contribute to a single update: Following the release of MiMo-V2.6, tool-call repetition emerged as one of the most noticeable issues in agentic settings: the model would sometimes issue the same or highly similar tool calls repeatedly, consuming time and context without making progress. This checkpoint mitigates it.
> [!IMPORTANT] > **This is the MOPD upgrade of the MiMo-V2.6-Pro-RL checkpoint.** > > - **MOPD2** (👉 **Technical Report §5.6**) > Fuses several domain-specialized teachers into one model, extending to domains where reliable training-time verification is hard, such as long-horizon game development, scientific research and embodied intelligence. > - **Diagnosing and Mitigating Tool-Call Repetition in MiMo-V2.6** (👉 **Technical Blog**) > An easy-to-overlook failure mode in which the model keeps issuing the same or highly similar tool calls, appearing busy while making no progress. Nothing fails outright, so it tends to go unnoticed. The MOPD stage handles it efficiently, with a short specialized-teacher run that converges quickly. MOPD2 distills several domain-specialized teachers into the student on-policy. The teachers fall into two families: **mixRL teachers**, trained on verifiable tasks, and **SFT teachers**, trained on synthetic demonstrations for open-domain tasks where a reliable reward is hard to design. Three streams contribute to a single update: Following the release of MiMo-V2.6, tool-call repetition emerged as one of the most noticeable issues in agentic settings: the model would sometimes issue the same or highly similar tool calls repeatedly, consuming time and context without making progress. This checkpoint mitigates it.
Play around! 🗨️ Xiaomi MiMo Studio 🎨 Xiaomi MiMo API Platform **MiMo-V2-Flash** is a Mixture-of-Experts (MoE) language model with **309B total parameters** and **15B active parameters**. Designed for high-speed reasoning and agentic workflows, it utilizes a novel hybrid attention architecture and Multi-Token Prediction (MTP) to achieve state-of-the-art performance while significantly reducing inference costs. MiMo-V2-Flash creates a new balance between long-context modeling capability and inference efficiency. Key features include:
