Xiaomi is the newest firm to launch an open-weight AI mannequin – MiMo-V2.5 claims to be a “main step ahead in agentic functionality and multimodal understanding.”
Xiaomi has shared varied benchmark outcomes that examine MiMo-V2.5 in opposition to the likes of the just lately launched DeepSeek-V4, Kimi K2.6, Claude Opus 4.6, Gemini 3.1 Professional and Xiaomi’s older MiMo-V2-Professional.
The corporate claims that MiMo-V2.5 achieved best-in-class efficiency on its in-house agentic duties benchmark. On the interior MiMo Coding Bench, the smaller V2.5 mannequin matched the bigger V2.5-Professional at half the associated fee. In different benchmarks that take a look at the mannequin’s picture and video understanding, V2.5 is degree with closed-source fashions, says Xiaomi.
MiMo-V2.5 evaluated on coding and agentic duties.
The mannequin was educated on 48 trillion tokens and is natively multimodal with assist for textual content, picture and video knowledge. Xiaomi has revealed two variations: MiMo-V2.5 with 310B complete parameters (15B energetic) and MiMo-V2.5-Professional with 1.02T complete parameters (42B energetic). The mannequin helps 1 million tokens of context.
MiMo-V2.5 evaluated on picture and video understanding
You may obtain the mannequin from Hugging Face and run it your self, however you will have one thing like a kitted-out Mac Studio to do it – shopper GPUs don’t have sufficient VRAM (no, not even the Nvidia RTX 5090).
You may check out Xiaomi MiMo-V2.5 within the AI Studio (which doesn’t load on the time of writing) or use it through the official API. Or, as talked about above, obtain it and run it domestically, if in case you have the means to take action.
Supply
