diff --git a/README.md b/README.md
index 9918b64..8757062 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,15 @@ Think of it as a translation layer: use JSON programmatically, and encode it as
 
 ## Why TOON?
 
-AI is becoming cheaper and more accessible, but larger context windows allow for larger data inputs as well. **LLM tokens still cost money** – and standard JSON is verbose and token-expensive:
+AI is becoming cheaper and more accessible, but larger context windows allow for larger data inputs as well. **LLM tokens still cost money** – and standard JSON is verbose and token-expensive. TOON offers a more compact alternative:
+
+<table>
+<tr>
+<th>JSON</th>
+<th>TOON</th>
+</tr>
+<tr>
+<td>
 
 ```json
 {
@@ -76,8 +84,29 @@ AI is becoming cheaper and more accessible, but larger context windows allow for
 }
 ```
 
+</td>
+<td>
+
+```toon
+context:
+  task: Our favorite hikes together
+  location: Boulder
+  season: spring_2025
+
+friends[3]: ana,luis,sam
+
+hikes[3]{id,name,distanceKm,elevationGain,companion,wasSunny}:
+  1,Blue Lake Trail,7.5,320,ana,true
+  2,Ridge Overlook,9.2,540,luis,false
+  3,Wildflower Loop,5.1,180,sam,true
+```
+
+</td>
+</tr>
+</table>
+
 <details>
-<summary>YAML already conveys the same information with <strong>fewer tokens</strong>.</summary>
+<summary>YAML already achieves <strong>fewer tokens</strong> than JSON, but TOON goes further.</summary>
 
 ```yaml
 context:
@@ -113,22 +142,6 @@ hikes:
 
 </details>
 
-TOON conveys the same information with **even fewer tokens**, while keeping the hikes in a clear tabular layout:
-
-```toon
-context:
-  task: Our favorite hikes together
-  location: Boulder
-  season: spring_2025
-
-friends[3]: ana,luis,sam
-
-hikes[3]{id,name,distanceKm,elevationGain,companion,wasSunny}:
-  1,Blue Lake Trail,7.5,320,ana,true
-  2,Ridge Overlook,9.2,540,luis,false
-  3,Wildflower Loop,5.1,180,sam,true
-```
-
 ## Key Features
 
 - 💸 **Token-efficient:** typically 30-60% fewer tokens on large uniform arrays vs formatted JSON[^1]