
Open omnimodal intelligence, trained in public
MiMo-V2.6 is Xiaomi’s open omnimodal model family for long-horizon agent work. Pro and Flash handle text, images, audio and video with 1M context, while Xiaomi is also releasing the technical report, RL environments and training code behind the public post-training run.
MiMo-V2.6 is Xiaomi's open-source omnimodal AI model designed for long-horizon tasks, capable of processing text, images, audio, and video with a 1M context. The release includes a technical report, reinforcement learning environments, and training code.
Scored deterministically. Only candidates that fire a story trigger are sent to a model, so this one has no written angle.
Gaps in our data, not findings about the product. Their weight is redistributed across the 5 we did measure.
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.