Update README.md

README.md

@@ -14,7 +14,7 @@ library_name: transformers
 
 # VibeThinker-1.5B
 ## Introduction
-VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium. Most remarkably, it surpasses the initial DeepSeek R1 model—which is over 400 times larger—across three challenging mathematical benchmarks: AIME24 (80.9 vs. 79.8), AIME25 (73.7 vs. 70.0), and HMMT25 (50.1 vs. 41.7).
+VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium.
 
 ![image](https://cdn-uploads.huggingface.co/production/uploads/64d1faaa1ed6649d70d1fa2f/6MgmRUkEubiEv4mT_wslp.png)