In a significant development, xAI has made waves in the AI Chatbot world with the impressive performance of its Grok-2 and Grok-2-Mini models on the LMSys Chatbot Arena leaderboard.
Grok-2 has secured the second spot, tying with the latest Gemini model and surpassing the mighty GPT-4o.
Grok-2’s standout performance is particularly noteworthy in the mathematical tasks category, where it has claimed the top position. The model has also excelled in hard prompts, coding, and instruction-following, earning the second spot in these areas.
Grok-2-Mini has also made its mark, securing the fifth position on the leaderboard.
The model has undergone significant speed enhancements, now performing twice as fast as before, thanks to xAI’s inference team’s efforts in rewriting the inference stack using SGLang.
Chatbot Arena update❤️🔥
— lmsys.org (@lmsysorg) August 23, 2024
Exciting news—@xAI's Grok-2 and Grok-mini are now officially on the leaderboard!
With over 6000 community votes, Grok-2 has claimed the #2 spot, surpassing GPT-4o (May) and tying with the latest Gemini! Grok-2-mini also impresses at #5.
Grok-2 excels in… pic.twitter.com/5lyQgratJQ
The Grok-2 family of models are now available in beta for testing on X, and users can even generate images using the FLUX.1 image generation model.
With these impressive results, xAI has undoubtedly shaken up the chatbot arena, and the world is eager to see what the future holds for these innovative models.