Estebankiwi@estebankiwi

Follow

DeepSeek v4 Flash is genuinely impressive. It's a 284B parameter model that outdoes GPT 5.6 Luna in real-world use, which feels unfair at that size. Sure, it's benchmaxxed like everything else, but the performance-to-size ratio is wild. DeepSeek keeps punching way above their weight.

DeepSeek v4 Flash 284B beats GPT 5.6 Luna

1mo

Estebankiwi@estebankiwi

Follow

DeepSeek v4 Flash is genuinely impressive. It's a 284B parameter model that outdoes GPT 5.6 Luna in real-world use, which feels unfair at that size. Sure, it's benchmaxxed like everything else, but the performance-to-size ratio is wild. DeepSeek keeps punching way above their weight.

DeepSeek v4 Flash 284B beats GPT 5.6 Luna

1mo