Did that Gemini have tool usage (Python or Lean or similar) or did it solve the problems using model inference alone?
LLMS
-
LLMs Solving IMO Without Specific Competition Context
By
–
Como indican aquí sí se le ha facilitado información en su contexto, específico de la competición IMO y me pregunto si OpenAI lo habrá hecho de forma similar o no, pero sería espectacular ver a un LLM superar la competición sin ningún precondicionamiento.
-
LLM Chat Apps Need Better Documentation Access Tools
By
–
I wish LLM chat apps would run a form of RAG for this – or just provide a tool called "help_answer_questions_about_abilities()" which, when called, dumps a few thousand extra tokens of documentation into the context Feels like low hanging fruit for a significant usability win
-
Google Gemini Deep Think wins medal with more powerful English version
By
–
Además, a diferencia del año pasado, Google este año logra medalla con Una versión más potente de Gemini Deep Think operando directamente en inglés, y no con un sistema especializado para la competición como fue AlphaGeometry
-
OpenAI and Gemini Tie at 35/42 on Challenge Benchmark
By
–
Interestingly, both OpenAI and Gemini achieve the exact same score: 35/42 – and both teams solved problems 1-5 but did not solve 6, the most challenging problem
-
Google Gemini Achieves Gold at International Mathematics Olympiad
By
–
It wasn't just OpenAI who got gold on the International Mathematics Olympiad this year – here's Google Gemini's result
-
Question about Rasbt’s Qwen3 Analysis
By
–
qq did you see @rasbt 's analysis and questions on qwen3?
-
LLMs Solve Hard Math Problems Through Generalization
By
–
It wasn't just OpenAI. Google also used a general purpose model to solve the very hard math problems of the International Math Olympiad in plain language. Last year they used specialized tool use Increasing evidence of the ability of LLMs to generalize to novel problem solving
-
IMO Gold Model Expands Beyond Reasoning Into General Purpose AI
By
–
Our IMO gold model is not just an "experimental reasoning" model. It is way more general purpose than anyone would have expected. This general deep think model is going to be shipped so stay tuned!
-
Gemini with Deep Think Achieves Gold Medal at IMO
By
–
It looks like an advanced version of Gemini with Deep Think just solved 5 out of the 6 IMO problems, earning 35 total points, and officially achieving gold-medal level performance. https://
deepmind.google/discover/blog/
advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/
… Congrats on the achievement @lmthang Can’t wait to play with this model