An advanced Gemini Deep Think model produced natural-language solutions to five of the six 2025 International Mathematical Olympiad problems, earning 35 of 42 points under the official coordinators’ grading.
An advanced Gemini Deep Think model produced natural-language solutions to five of the six 2025 International Mathematical Olympiad problems, earning 35 of 42 points under the official coordinators’ grading.
An advanced Gemini Deep Think model produced natural-language solutions to five of the six 2025 International Mathematical Olympiad problems, earning 35 of 42 points under the official coordinators’ grading.
The result demonstrates gold-medal-level performance on known competition problems with direct natural-language input and output.
Can an AI system solve the official IMO problems in natural language within the contest time limit?
Publication dates and editorial changes.
Allow optional Google Analytics to help improve AIProofWatch? Privacy details.
