Update README.md

README.md

@@ -50,11 +50,11 @@ base_model:
 
 ## **HealthBench**
 
-[**HealthBench**](https://arxiv.org/abs/2505.08775) is an open-source medical evaluation benchmark released by OpenAI, designed to assess the performance of Large Language Models (LLMs) in real-world medical environments through highly simulated multi-turn dialogues. AntAngelMed achieved outstanding performance on this benchmark, ranking first among all open-source models, with a particularly significant advantage on the challenging HealthBench-Hard subset.
+[**HealthBench**](https://arxiv.org/abs/2505.08775) is an open-source medical evaluation benchmark released by OpenAI, designed to assess the performance of Large Language Models (LLMs) in real-world medical environments through highly simulated multi-turn dialogues. AntAngelMed achieved outstanding performance on this benchmark, ranking first among all evaluated models, with a particularly significant advantage on the challenging HealthBench-Hard subset.
 
-![](https://intranetproxy.alipay.com/skylark/lark/0/2026/png/135556672/1767580967360-839e73a3-38b7-41d2-92e2-eb27b18774c1.png)
+![](https://raw.githubusercontent.com/lishuang70345/AntAngelMed/refs/heads/main/Figures/Fig1%20%7C%20AntAngelMed%20ranks%20first%20among%20open-source%20models%20on%20HealthBench.png)
 
-**Figure | AntAngelMed ranks first among open-source models on HealthBench**
+**Figure | AntAngelMed ranks first among all evaluated models on HealthBench**
 
 ## **MedAIBench**