Update README.md

README.md

@@ -41,8 +41,22 @@ We argue that the key to advancing towards AGI lies in the synergy effect—a ca
 <img src='https://cdn-uploads.huggingface.co/production/uploads/647773a1168cb428e00e9a8f/-Asn68kJGjgqbGqZMrk4E.png'  width=950px>
 </div>
 
+
+---
+
+This project introduces **General-Level** and **General-Bench**.
+
+---
+
+## 🌐🌐🌐 Keypoints
+
+- [🏆 Overall Leaderboard](#leaderboard)
+- [🚀 General-Level](#level)
+- [🍕 General-Bench](#bench)
+
 ---
-🏆🏆🏆 Overall Leaderboard
+
+# 🏆🏆🏆 Overall Leaderboard<a name="leaderboard" />
 
 <div align="center">
 <img src='https://cdn-uploads.huggingface.co/production/uploads/647773a1168cb428e00e9a8f/32goE-PYuwOwRvYg4GcfK.png'  width=900px>
@@ -51,10 +65,10 @@ We argue that the key to advancing towards AGI lies in the synergy effect—a ca
 
 ---
 
-This project introduces **General-Level** and **General-Bench**.
+# 🚀🚀🚀 General-Level<a name="level" />
 
----
-🚀🚀🚀 **General-Level**: a 5-scale level evaluation system with a new norm for assessing the multimodal generalists (multimodal LLMs/agents). The core is the use of Synergy as the evaluative criterion, categorizing capabilities based on whether MLLMs preserve synergy across comprehension and generation, as well as across multimodal interactions. 
+**A 5-scale level evaluation system with a new norm for assessing the multimodal generalists (multimodal LLMs/agents).  
+The core is the use of <b style="color:red">synergy</b> as the evaluative criterion, categorizing capabilities based on whether MLLMs preserve synergy across comprehension and generation, as well as across multimodal interactions.**
 
 
 <div align="center">
@@ -73,7 +87,16 @@ This project introduces **General-Level** and **General-Bench**.
 
 
 ---
-🌐🌐🌐 **General-Bench**, a companion  massive multimodal benchmark dataset, encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325K instances. 
+
+# 🍕🍕🍕 General-Bench<a name="bench" />
+
+**A companion  massive multimodal benchmark dataset, encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325K instances.**
+
+
+We set two data domains:
+- [**General-Bench-Openset**](https://huggingface.co/datasets/General-Level/General-Bench-Openset) with inputs and labels of samples all publicly open, for open-world use (e.g., academic experiment).
+- [**General-Bench-Closeset**](https://huggingface.co/datasets/General-Level/General-Bench-Closeset) with only sample inputs available, which participants can use for ranking in our leaderboard.
+
 
 <div align="center">
 <img src='https://cdn-uploads.huggingface.co/production/uploads/647773a1168cb428e00e9a8f/d4TIWw3rlWuxpBCEpHYJB.jpeg'>