US EditionDeepMind's Gemini Earns Official IMO Gold as OpenAI Awaits Confirmation
SUNSHINE COAST, QUEENSLAND, AUSTRALIA, JUL 22 – OpenAI and Google DeepMind AI models solved five of six problems at the 2025 International Mathematical Olympiad, scoring 35 out of 42 points and surpassing last year's silver medal performance.
- OpenAI announced on July 19, 2025, that its experimental model achieved gold medal performance at the 2025 International Mathematical Olympiad .
- The model’s success follows years of AI advancement with general-purpose reasoning approaches rather than highly specialized domain models for math problems.
- The model successfully solved five out of six IMO problems, scoring 35 out of 42 points within the 4.5-hour time limit, which corresponds to a gold medal performance ranking it within the highest tier of participants globally.
- OpenAI described the model as an "experimental reasoning LLM" built on new research techniques, and cautioned it will not release this model for many months despite announcing GPT-5 soon.
- This milestone suggests scalable general-purpose AI can rival top human mathematicians and may accelerate AI contributions to scientific discovery in the future.
112 Articles
112 Articles
Human teens beat AI at an international math competition
For the first time ever, AI models achieved prestigious gold-level scores at the International Mathematics Olympiad, one of the world’s premiere math competitions. Their success is an undeniable bragging right for the technology’s biggest supporters. But as it stands, Google and OpenAI’s most cutting-edge, experimental AI programs still can’t beat an extremely smart teenager. It may seem ironic, but complex mathematics is still one of AI’s bigge…
In order to demonstrate their skills, AI providers presented their software with the same tasks as the international mathematics Olympics. ChatGPT manufacturer OpenAI, however, made an early start.
Gemini Deep Think, unlike the "brother" of ChatGpt, officially participated in the competitions. We could find ourselves one step away from solving math problems until now unsolved by us humans
In a top-level international mathematics competition, humans have beaten generative artificial intelligence (AI) models developed by Google and OpenAI, even though these programs themselves achieved gold medal-level results for the first time.
Google DeepMind announced yesterday that an advanced version of its artificial intelligence system (IA) Gemini Deep Think has achieved gold medal level performance at the International Mathematical Olympiad (IMO) held this 2025 in Australia.
Coverage Details
Bias Distribution
- 43% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
