DeepThink is exceptionally good when powered by an inference-time scaling law that we showed in our Aletheia paper https://
arxiv.org/abs/2602.10177! These were benchmarked on our IMO-ProofBench graded by experts, which was the north-star metric leading to our IMO-gold achievement. Amazing
LLMS
-
DeepThink Achieves IMO Gold Using Inference-Time Scaling
By
–
-
Aletheia: AI Math Research Agent Solves Erdős Open Problems
By
–
Yesterday we just shared Aletheia, our math research agent that enables autonomous math research and solving Erdos open problems. Yes, this Gemini 3 deep think was *the* deep think. It's launched! nitter.net/YiTayML/status/2021750… Yi Tay (@YiTayML) Introducing Aletheia, a math research agent powered by an advanced version of Gemini Deep Think that produces publishable math research (two papers, one completely automatic and another with human-AI collaboration) and solved multiple open Erdős problems. 😀🔥 Paper link below! 👇 — https://nitter.net/YiTayML/status/2021750645666328779#m
-
Gemini 3 Deep Think: New AI Model with Gold-Standard Performance
By
–
Gemini 3 Deep Think is here! 😎 This model is not only super strong in math and coding (IMO gold and 3455 codeforces ELO), it is also gold standard in physics and chemistry olympiads. 😃 Also sets new records on ARC-AGI-2 and HLE. Proud to be a (core) member of the Deep Think team. 🦾😆. Feeling the AGI!
-
Google DeepMind Launches DeepThink V2 Reasoning Model
By
–
Congrats to the whole Deep Think team from @GoogleDeepMind for this amazing milestone of #DeepThink V2 launch! Such a great a model that powers so many state-of-the-art results from reasoning (ARC-AGI2) to deep knowledge (Humanity's Last Exam), multimodality (MMMU-Pro), coding
-
Google upgrades Gemini 3 Deep Think to 84.6% on ARC-AGI-2
By
–
BREAKING : GOOGLE UPGRADED GEMINI 3 DEEP THINK! IT ACHIEVED SOTA SCORE OF 84.6% ON ARC-AGI-2 BENCHMARK. GEMINI IS BACK!
-
Gemini 3 Deep Think Updated: Faster, Smarter PhD-Level Reasoning
By
–
An updated & faster Gemini 3 Deep Think is taking off! 🚀 Our smartest mode to date!™️ PhD-level reasoning to the most rigorous STEM challenges (models' gotta think harder). Gold medal-level results on Physics & Chemistry Olympiads. 🧪💻 Full details: bit.ly/4kzBLqq
→ View original post on X — @oriolvinyalsml, 2026-02-12 16:20 UTC
-
AI-Generated Code Quality and Iterative Design Improvement
By
–
Somewhere in between hand-written source and machine slop… there is a new kind of code. It starts out kinda functional but its design feels very far below average, takes multiple complete rewrites and many more review rounds (pushing back against regression to the mean), and
-
Gemini 3 Deep Think Upgrade Blends Science with Engineering
By
–
Gemini 3 Deep Think is getting an upgrade 🧠 By blending deep scientific knowledge with advanced engineering utility, Deep Think now moves beyond abstract theory to drive practical applications.
— Google AI (@GoogleAI) 12 février 2026
Researchers are already using it to accelerate their work in the real world:
—… pic.twitter.com/O5z6g4Wf3aGemini 3 Deep Think is getting an upgrade By blending deep scientific knowledge with advanced engineering utility, Deep Think now moves beyond abstract theory to drive practical applications. Researchers are already using it to accelerate their work in the real world: —
-
MLA Uses DSA Underneath According to DeepSeek V3.2
By
–
I'd say it the other way around: MLA uses DSA underneath, but that's right! E.g., from the DeepSeek V3.2 paper: