GPT4.1 is nowhere near DeepSeek v3's performance
GPT4.1 is nowhere near DeepSeek v3's performance
GPT 4.1. is nowhere near DeepSeek V3's 0324 performance despite inference costs that are higher than Gemini 2.5 Pro.
OpenAI is having a difficult time and is certainly the LLM with the worst cost/performance ratio. GPT5 seems to be further away than ever. What is OpenAI doing wrong?