DeepSeek V4 Flash

Five prompts, seven models, five languages — a first look at a benchmark that doesn't exist yet, testing what LLMs do with government talking points.

When the ground truth is one person's taste, agreement with strangers is the wrong bar. Stability with yourself is the right one.

DeepSeek passes a simple test that stumps GPT and Claude. Why can't Western models stay in character?

A million-token context window at 2% the KV-cache cost — and prose that actually breathes. Here's what makes V4 different.