Grok 4 had lower lmarena scores than I had projected based upon the amount AI training compute used. I had projections for Grok 3.5 which was renamed Grok 4. We do not have elo lmarena score for Grok ...
Elon Musk-owned xAI is testing Grok 4.20, a new model update to Grok 4, which already competes with GPT-5 in some benchmarks, such as ARC-AGI 2. GPT-5 is one of the best models for coding, and it ...
BEIJING, CHINA - AUGUST 24: In this photo illustration, the logo of Grok is displayed on a smartphone screen with the xAI logo in the background on August 24, 2025 in Beijing, China. Elon Musk's xAI ...
Elon Musk's AI company xAI has announced the release of the Grok 2.5 model as an open source project, featuring an estimated 268 billion parameters. This initiative aims to enhance the company's ...
An AI model on OpenRouter is called Sonoma Sky Alpha is likely a preview of XAI Grok 4.2. It highlights xAI’s rapid progress in compute power, model diversity, and specialized applications like coding ...
Is Grok 4.2 the most intelligent coding model we’ve seen yet? With its release in January 2026, this AI powerhouse has already sparked conversations across the tech world. In this comparison, World of ...
Hosted on MSN
New tests show ChatGPT-5 is more accurate than GPT-4o – Grok still struggles with hallucinations
ChatGPT-5 scores a low 1.4% on the Hallucination Leaderboard This puts it ahead of ChatGPT-4 which scores 1.8% and GPT-4o, which scores 1.49% Grok 4 is much higher at 4.8%, with Gemini-2.5 Pro at 2.6% ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results