Microsoft AI's pre-trained foundation model with about 80B active parameters; post-training unfinished and not yet available.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
MAI Base 2 is a pre-trained foundation language model from Microsoft AI (MAI). According to a creator summary of the announcement, it has roughly 80 billion active parameters, and Microsoft claims it outperforms every open-weight model it tested. These claims come from Microsoft and have not been independently verified here.
The model is a base model: post-training was reportedly not finished, and it is not publicly available. Reviewers could therefore not test it. It appears to relate to Microsoft's "Frontier Pre-training at Microsoft AI" work, which is mentioned on the MAI website, and it would presumably underpin later MAI models such as MAI Thinking 1 and MAI Code 1.1 Flash. The provided pages do not confirm this.
No access method, pricing, license, architecture details or release date were found in the provided material.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Microsoft's newly pre-trained model with 80B active parameters, claimed to outperform every open-weight model tested. Post-training isn't finished and it isn't available, so the creator couldn't test it.
Closest neighbours by meaning, not just by category.
Model · Microsoft
Microsoft AI's in-house MAI model family covering reasoning, code, speech, transcription, image and cybersecurity.
Model · Microsoft
Microsoft AI's mixture-of-experts reasoning model, in private preview via Microsoft Foundry.
Model · Microsoft
Microsoft AI's text-to-speech voice model with expressive output across multiple languages.
Model · Microsoft
Microsoft AI's low-latency text-to-speech model in the MAI model family, designed for long-form expressive speech.
Model · Baidu
Baidu's open-weights 280B-parameter sparse MoE base model (14B active) with 1M-token context, released pre-post-training.
Model · Microsoft
Microsoft's coding-focused AI model in the MAI family, announced with few public details.
