A new model, GPT-6 Astra, has achieved an Elo rating of 2,340 on the ChessBench benchmark, placing it at #11 in the rankings. This performance indicates a significant step forward in AI's chess-playing capabilities. AI
IMPACT This benchmark result suggests advancements in AI's strategic reasoning and problem-solving abilities, potentially impacting future AI development.
RANK_REASON The cluster reports a benchmark score for a new AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →