Grok 4 trails Google and OpenAI models despite Musk’s “smartest AI” claim

Elon Musk claimed that xAI’s new Grok 4 chatbot was “the smartest AI in the world,” but recent rankings from UC Berkeley’s LMArena leaderboard tell a different story. The model placed third overall, trailing behind Google’s Gemini 2.5 and OpenAI’s o3 and 4o reasoning models, highlighting the gap between Musk’s bold claims and actual performance metrics.

What you should know: Grok 4 achieved third place in the LMArena leaderboard rankings, despite Musk’s assertion that it was superior to all competitors.

• Google’s Gemini 2.5 placed first overall, while OpenAI’s o3 and 4o reasoning models tied for second place.
• Grok 4 tied with GPT-4.5 for third place in both overall rankings and text generation categories.
• The UC Berkeley-developed platform crowdsources AI model rankings by having users score responses across categories including creative writing, coding, math, and vision.

What Musk claimed: The xAI founder made sweeping statements about Grok 4’s capabilities that don’t align with independent testing results.

• “Grok 4 is smarter than almost all graduate students in all disciplines, simultaneously,” Musk bragged.
• He declared Grok 4 “the smartest AI in the world” despite lacking supporting evidence from standardized benchmarks.

The leaderboard controversy: Recent criticism has raised questions about the reliability of the LMArena rankings themselves, potentially complicating the assessment of AI model performance.

• A consortium of AI researchers led by machine learning firm Cohere published a study alleging “systematic issues that have resulted in a distorted playing field.”
• The researchers claimed the arena conducts “undisclosed private testing” before releasing public scores and can retract rankings at will.
• Meta was caught using a different version of LLaMA 4 for leaderboard testing than what was publicly released, leading to an apology and credibility concerns.

Why this matters: The disconnect between executive claims and independent benchmarks reflects broader challenges in accurately measuring and communicating AI capabilities to the public.

• Musk has a documented history of making exaggerated claims across his professional and political activities.
• The controversy surrounding leaderboard methodology highlights the difficulty of creating standardized, reliable AI evaluation systems.
• These measurement challenges make it harder for consumers and businesses to make informed decisions about AI tools.