Nadav Outmezguine

Particles/Astroparticles/DM Postdoc at @UCBerkeley and @BerkeleyLab

[stochasm @stochasticchasm]

okay live reading/reacting thread here, there's a ton to go through

[Adam Sadovsky @asadovsky]

Today we announced MAI-Thinking-1, a strong generalist and reasoning LLM built from the ground up without distilling third-party models. 97% on AIME 2025; 53% on SWE-Bench Pro; preferred by human raters over Sonnet 4.6 (blind side-by-side).

Tech report: https://t.co/qxGQWX5cOt

[Hanxiao Liu @Hanxiao_6]

Happy to share our recent work!

[Hanna Hajishirzi @HannaHajishirzi]

MAI-Thinking-1 is out!

Excited to share what we are building and how climbing from scratch (no distillation) actually works: simple recipes, rigorous science, self-distillation, patience, and great infra.

Check out our tech report has the full story of our RL climbs.
https://t.co/aLW40sWz4d

[Mustafa Suleyman @mustafasuleyman]

Super excited to announce seven new world-class MAI models today. They represent what we consider a new era in AI designed to keep you in control and on the frontier.
First is our text foundation model, MAI-Thinking-1, exceptionally strong on reasoning and SWE tasks.
- It’s a 35B active parameter MoE with a 256K context window. Independent human raters on Surge prefer it for overall quality in blind side-by-sides versus Sonnet 4.6, and it’s achieved 97% on AIME 2025, the key measure of its general-purpose reasoning abilities.
- It's at 53% on SWE Bench Pro, placing it right alongside Opus 4.6 on one of the toughest coding benchmarks.
- And since we co-designed our models with our own silicon, MAI-Thinking-1 is optimized on our MAIA 200 chip. Benchmarking head-to-head against the GB200, we see 30% better performance per dollar as well as a 1.4x performance-per-watt gain when running our MAI models on the MAIA 200 end-to-end.

Next is MAI-Image-2.5 and its Flash variant. Two super strong models now at #2 on the leaderboards, surpassing the score of Nano Banana 2 on image editing.

Last for now is MAI-Code-1-Flash, our new inference efficient coding model, especially tuned for VS Code and GitHub Copilot CLI.
- Code-1-Flash achieves 51% on SWE Bench Pro, despite having just 5B parameters, putting it closer to Haiku in size but cheaper in cost.

All of this is the foundation for Microsoft Frontier Tuning. It lets you customize our models to create custom, company-specific agents that only you control. You can make our model, your model. Your data. Your agents. Your moat.

Early adopters are already seeing a difference. When we tuned our models for McKinsey’s tasks, MAI delivered the highest win rate, outperforming GPT-5.5 on quality, while being 10x lower on cost.

Also really excited to be collaborating with the amazing team at Mayo Clinic to jointly train a new frontier AI model for healthcare.

Our announcements today mark another milestone on the road to humanist superintelligence. You can learn more and about our other new models in our latest blog: https://t.co/v65eop5Ixq

[Anastasios Nikolas Angelopoulos @ml_angelopoulos]

Are you guys clocking how big this is

[Nadav Outmezguine @NadavOut]

@GutmanYotam @notevildvir רק עכשיו הבנתי שזה טרנטינו ולא דני רופ

[Nadav Outmezguine @NadavOut]

@Kralizec18 @gilgameshinnyc @StopAntisemites @UCBerkeley Yes. 100%

[Nadav Outmezguine @NadavOut]

@FeedTechILUncen לא

[Peyman Milanfar @docmilanfar]

Amen

[Nadav Outmezguine @NadavOut]

@four_form Oh man…

[Gideon Sa'ar | גדעון סער @gidonsaar]

החלטת נתניהו לפטר את שר הבטחון יואב גלנט היא מעשה של טירוף, המעידה על העדר מוחלט של שיקול-דעת. אין תקדים בתולדות ישראל לשר בטחון שפוטר בגלל שהתריע, כמתחייב מתפקידו, על סכנה ביטחונית. נתניהו נחוש לדרדר את ישראל לתהום. כל יום בו מכהן נתניהו בתפקידו מסכן את ישראל ועתידה.

[Nadav Outmezguine @NadavOut]

@cajohare You deserve a medal 🎖️

[🇱🇧🇻🇦𐤍𐤏𐤅𐤓 @nonabeleerf]

We will have peace soon enough. Despite Iran's scums deviding us.

[Nadav Outmezguine @NadavOut]

@DrDM777 @mc_limor מאד רוצה לראות את האינטגרל! :)

[Nadav Outmezguine @NadavOut]

@BenBetzalel מעניין לחזור אל התרגיל הזה עם תמונה פחות מוכרת

[Sasha Rush @srush_nlp]

Updating all my NeurIPS papers.

[Nadav Outmezguine @NadavOut]

@ChristiStoica @Anthony_Bonato Wanted to say the same! The thing they call mathematicians is actually physicists

[Eran @GrabinerEran]

אני לא יודע אם הסעודים מתואמים איתנו, מאמין שלא. אבל אכן קרו בשנים האחרונות שינויים שעשויים לגרום לסעודיה ואפילו לארה״ב לשמוח מפגיעה בתעשיית הנפט האיראנית. סעודיה מבזבזת הרבה מדי כסף וארה״ב הפכה להיות יצרנית הנפט הגדולה בעולם ויצואנית של נפט: