With a 4-0 win over Elon Musk's AI Grok 4 in the final, ChatGPT's o3 Large Language Model (LLM) took the crown at the first ...

He estimated Grok 4's skill at a lowly "800," while rating o3 at "1200." He described OpenAI’s o3 as looking "like a chess player" that was "fairly ruthless in conversions," indicating that the AI ...

Magnus Carlsen won the game without losing a single piece, while ChatGPT lost all its pawns, screenshots the Norwegian ...

World number one chess player Magnus Carlsen estimated Grok’s rating at approximately 800 and OpenAI’s model at around 1200, ...

Magnus Carlsen won the game without losing a single piece, while ChatGPT lost all its pawns, screenshots the Norwegian grandmaster shared on X showed. ChatGPT resigned the match. “I sometimes get ...

Grok 4 lost to OpenAI's o3 in the final of the Kaggle AI Exhibition Tournament on 7 August, 2025 () Sam Altman’s AI model has ...

Google aims to test the reasoning capabilities of ChatGPT, Gemini, Claude, and other AI models using a Bayesian skill-rating ...

The world’s top chess player defeated ChatGPT in an online match in only 53 moves. Magnus Carlsen won the game without losing a single piece, while ChatGPT lost all its pawns, screenshots the ...

The world’s top chess player defeated ChatGPT in an online match in only 53 moves. Magnus Carlsen won the game without losing a single piece, while ChatGPT lost all its pawns, screenshots the ...

Magnus Carlsen, the world’s top-rated chess player, beat ChatGPT in an online chess match, winning in just 53 moves without ...

In an AI-centric chess tournament, OpenAI's o3 model came out on top over Grok 4, but does this have any real implication on ...

As AI models increasingly ace conventional tests, researchers are looking for new benchmarking methods. Google is betting on ...