Research Scientist at @GoogleDeepmind
Zurich, Switzerland
Joined July 2009
- Tweets2.4K
- Following874
- Followers1.2K
- Likes10.4K
Pinned Tweet
How is next-token prediction capable of such intelligent behavior? I’m very excited to share our work, where we study the fractal structure of language. TLDR: thinking of next-token prediction in language as “word statistics” is a big oversimplification!
arxiv.org/abs/2402.01825
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
This is why scientists still cannot predict the double pendulum exactly.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Sharing early evals on Gemini 4 Carbon. Strongest model that we've seen so far for long-form research and answer quality, with a new SoTA on the Wide-And-Deep-Research (WANDR) benchmark. Coming soon to all Perplexity Pro and Max users inside Computer, once we have sufficient token capacity. Congrats @GoogleDeepMind!
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
We've launched our HLE-Diamond leaderboard, our independent evaluation of the refined 1,000-question version of Humanity's Last Exam, as part of v5 of the Artificial Analysis Intelligence Index
HLE-Diamond was released by @CAIS and @scale_AI after a year of cleaning and refining the original Humanity's Last Exam dataset with input from the research community. It has 1,000 closed-ended questions, split evenly between reasoning and knowledge, and 272 of them include an image.
We run every question once without tools, using the official HLE system prompt. GPT-5.6 Luna (medium) grades each answer against the reference answer with the official HLE judge prompt, and we report the share of questions judged correct (pass@1).
Key takeaways:
➤ Only 17 model variants (~13%) score above 50% today: Gemini 4 Carbon (high) leads at 69%, followed by Claude Opus 5.5 (max) at 68%
➤ Models score higher on reasoning than on knowledge: Over 90% of the models we measured do better on the reasoning portion of the benchmark. Gemini 4 Carbon (high) leads both, at 80% on reasoning and 59% on knowledge. Claude Opus 5.5 (max) and GPT-6 Astra (max) both score 78% on reasoning, and Opus 5.5 is ahead on knowledge, 58% vs 50%
➤ Open weights models trail by more than 30 points: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 37%, followed by MiniMax-M3.1-Flash at 28% and Kimi K3 (max) at 27%
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
A ‘hello world’ milestone for Project Suncatcher 🚀
After launching our prototype satellite a few weeks ago, we’ve now successfully sent a command up to orbit, booted up the TPU, ran the prompt, and received our first complete response back on earth - a haiku!
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Trump is reportedly planning to restart war with Iran after the election.
Some of us have been briefed on the war plan. And while I cannot disclose any details, I can say this: the plan is insane. It will not achieve objectives and will set off a new cycle of escalation.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
don't make me tap the sign: nitter.cf/rustyryan/status/21140…
but also, if you think it's benchmaxxed on AA, square this circle: the AA V5 linear model dropped yesterday.
Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index
Gemini 4 Carbon scores 59 on Intelligence Index v5, driven by leading performance in complex reasoning, knowledge, and scientific tasks. It also has large gains in coding and knowledge work, particularly when compared to other Gemini models, but it is not leading in all these areas.
As with launch of Gemini 4 Argon, Gemini 4 Carbon is being rolled out to selected users and is not yet publicly available. Google is offering a 50% launch discount, with no confirmed end date. All our charts and figures use standard pricing for both Gemini 4 Carbon and Argon.
Key results for Gemini 4 Carbon with high reasoning:
➤ Gemini 4 Carbon leads the Intelligence Index v5, with the #1 score in 4 of the 9 Index evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, AutomationBench-AA. Carbon makes substantial gains elsewhere but is not leading in coding and knowledge work
➤ Behind only Claude Opus 5.5 on coding agents: With Antigravity CLI, Gemini 4 Carbon (high) scores 59 only 3 points behind Claude Code with Claude Opus 5.5 (max, 62) on the Artificial Analysis Coding Agent Index. Carbon ranks second on both Terminal-Bench 4.0 (64%) and FrontierCode v1.1 (51%), behind Claude Opus 5.5 (max) at 56%. Google has historically underperformed in this area and so this improvement stands out
➤ Improved agentic knowledge work, but not yet leading: On AA-Briefcase, Gemini 4 Carbon (high) scores 1609 Elo, a 126-point improvement over Gemini 4 Argon (high, 1483), but still behind models including Grok 4.7 (xhigh, 1638), Muse Wonder (max, 1659) and Kimi K3.1 Pro (1678). The largest gain comes from Presentation, up 293 Elo to 1598, alongside a 120-point improvement in Analytical Quality to 1671
➤ Lower Cost per Task than Claude Opus 5.5 for comparable overall intelligence: Gemini 4 Carbon costs $7.76 per Intelligence Index task, ~23% less than Claude Opus 5.5 (max, $10.04) but ~1.2x GPT-6 Astra (max, $6.25). It uses 123k output tokens per task, 29% fewer than Claude Opus 5.5 (max, 173k). At the same $4/$20 standard pricing, its Cost per Task is in line with Gemini 4 Argon ($7.68), while scoring 9 points higher on the Intelligence Index
➤ Leading AA-Omniscience v1.1 score, with low hallucination: Gemini 4 Carbon scores 54 on our recently updated AA-Omniscience v1.1, 6 points ahead of Claude Opus 5.5 (max, 48) and 8 points ahead of Gemini 4 Argon (46). Accuracy (% correct) rises 10 points over Argon to 58%, while its hallucination rate rises from 4% to 11%. This is still the second lowest of any model, behind only Argon, compared with 50% for both Claude Opus 5.5 (max) and GPT-6 Astra (max)
Key model details:
➤ Context Window: 1M tokens
➤ Multimodality: Text, image, video, and speech input, with text output
➤ Pricing: $4/$20 per 1M input/output tokens, the same as Gemini 4 Argon’s standard pricing, with a 50% discount. Cached input tokens receive a 95% discount ($0.20 per 1M)
Congratulations to the @GoogleDeepMind team!
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
As promised: arxiv.org/pdf/2610.37364
@real_deep_ml
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Introducing Gemini 4 Carbon, it's a big jump over Argon which we released just 2 weeks ago.
Gemini 4 Carbon is SOTA on cyber, long horizon tasks, ranks #1 on Artificial Analysis V5, significantly improves on usability in domains like coding, and is more aligned.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Israeli journalist: "You are both first time voters. What are you voting based on?"
Israeli voter 1: "I don't want there to be Arabs in the county."
Israel voter 2: "Me neither."
Background: 56% of Israeli Jews want to expel all 2M Palestinian citizens of Israel, and 82% of Israeli Jews want to expel all Palestinains in Gaza to other countries. haaretz.com/israel-news/2025…
Turns out, for some voters, it is the only issue they care about: creating an Palestinianrein Israel the same way the Nazis created a Judenrein Germany.
source: instagram.com/reels/DfAdZBDB…
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
“Arabs don’t produce literature” is really something you can only say if you’ve never had a moment’s contact with genuine civilization. A mind totally consumed by television and self-help books.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Obama: "A Venezuelan billionaire wanted a pardon, so he paid one of Trump's personal lawyers $50 million... and lo and behold, the pardon falls out of the sky... We have never seen a president excel in straight-up grifting on your dime like this."
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
In January 2025 my mom’s lung cancer spread to her brain. The drug with the best chance of helping her was approved in China but not here.
A doctor told me, almost as an aside, that if she were Chinese she could buy it at a pharmacy.
So I flew to Shanghai and came home with 26 boxes in my luggage. That was 19 months ago. My mom is still here, still working, and in her words has had an amazing three years.
The drug was approved in China in 2023. The FDA approved it in July 2025. It still is not for sale here. I know of at least 30 Americans who have made the same trip.
I have been scared to tell this story because I worried it could cost my mom access to the medicine keeping her alive. But the problem matters more than my silence. These drugs need to be developed and available here, and that means FDA reform.
Art Allen at KFF Health News told our story this week. It also ran in The Washington Post.
kffhealthnews.org/health-ind…
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
In just the first 72 hours since Gemini 4 Argon launched, we processed ~25 trillion tokens, the demand for intelligence is incredible and still under appreciated!
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Kudos to the camera man. He decided NOPE - ain’t letting him pull this shit. Not today. Not on my watch.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
We added Gemini 4 Argon to our AutoResearchExam Pareto curve. It is 2-3 times cheaper compared to the other frontier models for almost the same ML engineering performance. Congratulations to the GDM team.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
It is a basic principle of American democracy that the government can’t selectively target individuals simply because of their political beliefs or what they say. But that’s exactly what the Trump Administration is doing to Congresswoman Ilhan Omar of Minnesota.
To understand why this is so appalling, it’s important to know the facts. Congresswoman Omar came to this country with her father when she was 12 years old. Five years later, her father became a naturalized citizen. If Ilhan had been 18 at the time, she would have had to apply for citizenship separately. But because she was 17, she became a naturalized citizen automatically.
Congresswoman Omar went on to graduate from college, work as a community organizer, become the first Somali-American legislator elected to public office in the U.S., and win a seat in Congress. There, she has been one of the Trump Administration’s fiercest critics, which has led the president to repeatedly single her out as someone who he believes does not belong in this country.
Now the Administration is actively trying to deport Congresswoman Omar, seemingly based solely on the unsubstantiated theory that she was actually 18 when her father was naturalized, and therefore is not a citizen. Federal agents have raided her home, confiscated personal records, and seized her phone — all to try and uncover a nonexistent smoking gun from 20 years ago that will somehow make their case.
Think about that. The full weight of the federal government is being brought down on a law-abiding elected official because she has dared to criticize the president. And it’s not the first time this has happened. Under President Trump, the Justice Department has repeatedly gone after those he considers his political enemies — from the Attorney General of New York, to the former head of the FBI, to members of the Federal Reserve.
In those cases, the prosecutions either stalled or were dismissed for having no basis in law, and the same is likely to happen in this case. But not before Congresswoman Omar’s life has been turned upside down, her legal bills have piled up, and she’s been forced to spend time fighting unsubstantiated charges instead of serving the people of Minnesota.
The fact that any president, or any administration, is willing to engage in such transparent efforts to intimidate someone should outrage all Americans, regardless of how they feel about Congresswoman Omar’s political views. Because if this becomes the new normal, there’s no reason to believe it will stop with her — or that future presidents, in either party, won’t do the same.
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
He saved our lives from the settler-terrorists who attacked the olive harvesters and journalists.
He and many other Palestinians who bravely risked their lives, defending their land.
Hey @the_andrey_x what was a masked Palestinian with a slingshot doing among you in that innocent "olive harvesting" at 1:29?
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Masked Israeli settlers attacked Palestinian villagers on Friday, setting olive groves on fire and slinging rocks.
Caught in the attack was Post photographer Heidi Levine. “They just kept kicking me and kicking me, like probably 50 times,” Levine said. wapo.st/4yt6dHY
Ibrahim Alabdulmohsin | إبراهيم العبدالمحسن retweeted
Argon has this amazing natural understanding of the world. It can do so many things from first principles.
Here's a pelican riding a bike, using fourier epicycles.
Video made by Argon.
Time-synced Lyria 3.5 music prompted by Argon.
Gemini 4 Argon is live.
blog.google/innovation-and-a…
There's a lot to show you.
