@User_2342111

2025-07-18 05:18:12

So makarte sentiments on Grok 4 is it was built to "break" Benchmark score but not to be actually useful ... users are calling "X" out on this since day of launch !

https://x.com/burkov/status/1944125708751745352

#Grok4 #AI #LLM #Benchmark #X #SocialMedia #OpenAI #GPT4 #LanguageModel #ArtificialIntelligence #Chatbot #Innovation #TechNews

So makarte sentiments on Grok 4 is it was built to "break" Benchmark score but not to be actually useful ... users are calling "X" out on this since day of launch ! https://x.com/burkov/status/1944125708751745352 #Grok4 #AI #LLM #Benchmark #X #SocialMedia #OpenAI #GPT4 #LanguageModel #ArtificialIntelligence #Chatbot #Innovation #TechNews

Grok 4 scores very poorly on Yupp, an LMArena competitor to which, probably, the LLM providers haven’t yet managed to finetune; below even Grok 3, with a score of 1142.

Claude Opus 4’s score, for comparison, is 1381.

So, all as I expected: when you don’t have more data and, as… pic.twitter.com/qeZ2dsFvqe
— Andriy Burkov (@burkov) July 12, 2025

0 Comments ·0 Shares ·310 Views