Update README.md

README.md

@@ -43,6 +43,10 @@ In MiroThinker-v0.2, we introduced three key improvements:
 
 Compared to v0.1, MiroThinker-v0.2 delivers consistent gains across benchmarks. For example, scores improved from **57.3 → 64.1** on **GAIA-Text-103** and from **17.0 → 29.4** on **BrowseComp-ZH**, reflecting substantial advancements in the model’s general research agent capabilities.
 
+<div>
+  <img src="https://huggingface.co/datasets/miromind-ai/MiroFlow-Benchmarks/resolve/main/assets/MiroThinker_v0.2_Performance_2.png" width="100%" alt="MiroThinker" />
+</div>
+
 ## Online Demo
 
 Welcome to try out our online demo [here](https://dr.miromind.ai/).
@@ -67,10 +71,6 @@ MiroThinker-v0.2 is trained on our large-scale, high-quality trajectory and pref
 
 To promote reproducibility and benefit the community, we decided to open-source the entire suite mentioned above. For more technical details, evaluation results, and usage tutorials, please visit our [GitHub repository](https://github.com/MiroMindAI/MiroThinker).
 
-<div>
-  <img src="https://huggingface.co/datasets/miromind-ai/MiroFlow-Benchmarks/resolve/main/assets/MiroThinker_v0.2_Performance_2.png" width="100%" alt="MiroThinker" />
-</div>
-
 ## License
 
 MiroThinker-v0.2 is licensed under Apache 2.0.