Can current MiniCPM5-2B/any best SOTA under 10B + modern harness beat pre-March 2025 frontier models like Grok 3/GPT-4o?

Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and Grok 3 were already enough for general chatting,search lookup, RP, etc. So if you brought those

中文全文翻译正在补齐，可先查看下方英文原文。

Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and Grok 3 were already enough for general chatting,search lookup, RP, etc. So if you brought those