Grok AI ranks no.1 for forecasting among LLMs — Elon Musk calls it ‘Best measure of intelligence!
Elon Musk is once again putting the spotlight on artificial intelligence, this time highlighting the predictive abilities of X’s AI chatbot, Grok. On his official X account, the billionaire shared a link to a live benchmark platform, urging users to test Grok’s forecasting prowess.
In his first tweet, Musk wrote, “Download the @Grok app and try Grok Expert mode. For serious predictions, Grok Heavy is the best.” He followed up with, “The ability to predict the future is the best measure of intelligence.”
FutureX: The benchmark for AI predictions
The link points to FutureX, a platform designed to evaluate how well large language models (LLMs) can predict real-world events. Developed by Jiashuo Liu and collaborators, FutureX presents AI agents with tasks spanning politics, economics, sports and cultural trends, scoring their predictions in real time.
FutureX also features a public leaderboard, allowing users to track model performance and fostering healthy competition. Its automated scoring ensures consistency and objectivity in assessing AI predictions.
Grok as a future predictive tool
By promoting the platform, Musk emphasises that Grok is not just a conversational AI but also a tool capable of anticipating future events. Highlighting its Expert and Heavy modes, he positions Grok as a model that combines advanced reasoning with predictive intelligence—an attribute he deems the “best measure of intelligence.”
Last month, the tech mogul announced that xAI has made its Grok 2.5 language model open source. He also revealed plans to release Grok 3 as open source within the next six months.
Grok 3 was unveiled by Musk and his team during a live-stream event in February. The billionaire has previously indicated that he intends to launch Grok 5 before the end of the year.
Musk wrote on X, “The @xAI Grok 2.5 model, which was our top model last year, is now open source. Grok 3 will be made open source in about six months.”
