OpenAI and Google DeepMind have achieved IMO Gold-level results in natural language reasoning tasks. Their models demonstrated this capability without requiring specialized training or external tools, performing within human time constraints. This breakthrough suggests significant advancements in AI's ability to understand and reason with complex information. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
RANK_REASON Frontier-lab model release with system card