14 articles
Grok 4.20 records the lowest hallucination rate at 22%, beating Claude 4.5 Haiku, MiniMax V2 Pro, and GLM-5 in factual accuracy.
xAI's Grok 4.20 scores 96.5% on the tau2-Bench Telecom test, outpacing Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro.
Grok 4.20 ranked #1 on the Alpha Arena leaderboard after turning $10,000 into $13,459. The model secured four of the top six positions across multiple strategies.
xAI's Grok 4.20 model has launched with weekly public updates driven by real user feedback, and early tests show strong relative performance in trading and forecasting benchmarks.
xAI's upcoming Grok 4.20 model arrives next week with stronger coding abilities and better front-end design performance compared to its predecessor.
An AI stock trading experiment reveals dramatic performance gaps among eight models testing live market strategies since late November. Grok 4 dominates the leaderboard with an 8.2% return, while others lag far behind or post significant losses.
Grok 4.20 swept the competition in Alpha Arena Season 1.5, claiming four of the top six leaderboard positions and becoming the only AI model to turn a profit in real-time stock trading.
xAI's Grok 4.20 beta independently derived a new mathematical formula that beats the strongest known theoretical bound, delivering a research-level breakthrough in probability theory within minutes.
Grok-4.20 jumped to the top spot on Alpha Arena's trading leaderboard with $16,968 in total equity. Multiple Grok variants grabbed top-five positions, leaving competing models far behind.
Grok 4.20 dominated Alpha Arena Season 1.5, taking first place with $16,171 in total equity while claiming four spots in the top ten rankings ahead of GPT-5.1, Gemini 3 Pro, and DeepSeek Chat V3.1.
Grok 4.20 has jumped to the top of AI trading rankings, beating every major competitor and racking up $16,159 in total equity. The model now holds three of the top five spots in current standings.
Experimental Grok 4.20 build ranks among top performers in Alpha Arena trading competition, delivering $3,000 profit and outpacing GPT-5.1 and DeepSeek models in latest benchmark results.
A mystery competitor in Alpha Arena's autonomous trading competition has been revealed as Grok 4.20 after taking first place. Each AI model traded independently with $10,000 in real markets over two weeks.
Elon Musk announces Grok 4.20, xAI's next-gen model that promises cross-language code intelligence, marking a shift from conversational AI to developer-focused programming assistant.
We use cookies to improve your experience on our site and to show you relevant advertising. To find our more, read our privacy policy and cookie policy
Saad Ullah
Alex Dudov
Peter Smith
Eseandre Mordi
Sergey Diakov
Artem Voloskovets
Victoria Bazir
