diff --git a/README.en.md b/README.en.md
index dc02cb5..2764737 100644
--- a/README.en.md
+++ b/README.en.md
@@ -6,6 +6,14 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x
**Live site:** https://bench.nagi.fun/
+
+ 
+ 
+ 
+ 
+
+
+
## Models vs harnesses
- **Model**: the weights and inference engine itself — GPT-5.5, Gemini 3.1 Pro, Claude Fable 5.
diff --git a/README.md b/README.md
index 243526a..10be4ca 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,14 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha
**线上站点：** https://bench.nagi.fun/
+
+
+
+
+
+
+
+
## 模型与 Harness 的关系
- **模型（Model）**：权重与推理引擎本身，如 GPT-5.5、Gemini 3.1 Pro、Claude Fable 5。