UAE Unveils Jais 3, a Suite of Arabic‑Native AI Models for Speech, Writing and Agent Tasks

Overview of Jais 3

Jais 3 understands spoken and written Arabic across dialects, generates Arabic text and performs practical tasks such as transcribing conversations, drafting documents and creating presentations. The suite comprises six open language models ranging from 900 million to 375 billion parameters, coupled with Jais Speech, a speech recognition model for Arabic and its varieties.

The models were trained on Modern Standard Arabic and regional dialects – including Emirati, Gulf and North African varieties – as well as the cultural knowledge carried by the language for more than 400 million speakers.

Haonan Li, senior research scientist at IFM, said: “Arabic AI needs to understand the language in its everyday context, which varies by geography and across generations. For example, we need to account for the many nuances in spoken Arabic, including when speakers slip into English or French mid‑sentence and back again. We built Jais 3 for Arabic as it’s really used.”

Richard Morton, vice president and executive director of IFM, added: “Jais has shown what the UAE’s long‑term investment in open AI research can deliver for the Arabic‑speaking world. With Jais 3, we are extending that foundation into speech and agents at a time when the UAE is putting AI to work across government and society — reflecting MBZUAI’s commitment to the UAE National AI Strategy 2031 and to building the research capability and national talent that will carry it forward.”

Performance and Benchmarks

IFM and Inception42 evaluated the models on an audited suite of 24 Arabic benchmarks, which they are releasing publicly alongside the models. The largest Jais 3 model leads open models on agentic tasks and matches the strongest on Arabic understanding. Jais Speech recorded the lowest average word and character error rates of any model compared, including commercial speech recognition services.

The advantage holds across sizes: the 3.7‑billion‑parameter model outperformed every competing open model of up to 5 billion parameters on Arabic and agentic tasks, while the 7‑billion‑ and 32‑billion‑parameter models earned the highest average Arabic scores among open models at their respective sizes.

Dr. Larry Murray, SVP Applied Science at Inception42, commented: “Jais 3 makes Arabic AI more practical for business use. Stronger reasoning and instruction following, combined with tool use, provide a foundation for multi‑step agentic workflows. With open models across a range of sizes, organizations can match these capabilities to their computing budgets and deployment needs.”

Jais Speech transcribes Modern Standard Arabic and dialects spoken across 19 Arab countries in real‑world conditions. It follows speakers as they switch between Arabic and languages such as English or French, keeping those words in their original script, identifies the dialect being spoken and can add Arabic vowel marks to a transcript. Paired with the language models, Jais Speech lets Jais 3 take spoken instructions in Arabic or English and act on them.

Jais 3 stays fluent and consistent across dialects and registers throughout a document and follows detailed instructions closely. In IFM’s and Inception42’s evaluations, the small and mid‑size Jais 3 models lead the open models compared on following complex Arabic instructions.

Ashish Koshy, CEO of Inception42, said: “Jais has defined what an Arabic large language model can be since the first release, and Jais 3 is the clearest step up yet. Building an Arabic LLM is not a translation exercise. It means training on the dialects people actually speak, the way they write, and the culture the language carries. That is the work we and IFM have done together across every generation of Jais, and it is why, by bringing together six new models, Jais 3 now leads on Arabic across every model size we have built.”

Technical Details and Availability

Jais 3 is the first adaptation of K2 Horizon to a new language. The six Jais 3 language models range from a 900‑million‑parameter model small enough to run on a phone to a 375‑billion‑parameter flagship. All share the same training recipe and agent capabilities, with a context window of 512,000 tokens, the longest of any Arabic‑native model.

Developers can choose the size that fits their hardware and budget. At 7 billion parameters, the average score on IFM’s and Inception42’s Arabic evaluations rises from 56.4 for the K2 Horizon base model to 79.6 for Jais 3, showing that an open foundation model can be adapted to a new language and culture without starting from scratch.

Each model ships with five training checkpoints, letting researchers trace its development and build from any stage. Government entities and enterprises in the UAE and beyond can adapt the models and decide where to deploy them, in line with sovereign AI requirements.

Jais 3 was created by the Institute of Foundation Models (MBZUAI) and Inception42, in collaboration with Cerebras Systems.

Jais 3 and Jais Speech are available today on Hugging Face, with deployment support for vLLM and SGLang. Learn more at https://ifm.ai/jais/