add blog/post.md

blog/post.md

@@ -1,8 +1,8 @@
-# Seb-9B-v2: A small model for the decisions your app makes all day
+# Seb-9B-v2: beats hosted Jev 1.13 on the Decision Index, at 22 ms, on your own hardware
 
-Most of what an application asks a language model to do is not writing. It is choosing. Which team gets this ticket? Is this email a phishing attempt? Should the robot stop? Does this contract allow that? These calls happen thousands of times a day. They need answers in milliseconds, and they should not require a hosted API.
+Seb-9B-v2 scores **59.16** on the Decision Index public index, ahead of hosted Jev 1.13 (57.96). It takes about **22 ms** a decision on one GPU or **88 ms** on a Mac, and nothing leaves your machine. On public decision rows it is level with Claude Haiku and gpt-6-luna. Put in front of Claude Opus as a first tier, it answered about half the requests itself and kept Opus-level accuracy overall, at an estimated **51% lower cost**.
 
-Seb-9B-v2 is built for exactly that. You give it a situation, a question, and a few options. In a single forward pass, it tells you how likely each option is. It generates no text, so there is nothing to parse. It runs on your own hardware, reads images, and supports both a standard chat API and the System One API.
+It is a decision model: you give it a situation, a question and a few options, and it returns a probability for every option in one forward pass. No text is generated, so there is nothing to parse. It reads images, takes inputs up to 32k tokens, and speaks both a regular chat API and the System One API.
 
 ![Seb-9B-v2](https://huggingface.co/ironbcc/Seb-9B-v2/resolve/main/blog/hero.png)