Update README.md

README.md

@@ -7,13 +7,13 @@ We introduce **SmallThinker-3B**, a new model fine-tuned from the [Qwen2.5-3b-In
 
 ## Benchmark Performance
 
-[Insert Benchmark Results Here - e.g., a table or bullet points showing performance on various metrics]
+| Model | AMPS_Hard Score |
+|---------|----------------|
+| SmallThinker | 58.0 |
+| GPT-4 (2024-08-06) | 54.0 |
+| Original 3B | 44.0 |
 
-*   **Example Metric 1:** [Score/Value]
-*   **Example Metric 2:** [Score/Value]
-*   **Example Metric 3:** [Score/Value]
 
-Please replace the example metrics with your actual benchmark results.
 
 ## Intended Use Cases