Update README.md

README.md

@@ -94,16 +94,17 @@ This represents a substantial improvement over earlier small-scale Colab experim
 
 ## GSM8K Accuracy Comparison
 
-| Model        | Accuracy (%) |
-|--------------|--------------|
-| Llama2-70B   | 56.8 |
-| Gemma-7B     | 46.4 |
-| Mistral-7B   | 52.2 |
-| Llama-3-8B   | 56.0 |
-| Qwen1.5-7B   | 62.5 |
-| **OpenMath** | **56.86** |
-
-
+| Model                      | Accuracy (%) |
+|---------------------------|-------------|
+| Qwen1.5-7B                | 62.50 |
+| Param2-17B-A2.4B-Thinking | 57.32 |
+| **OpenMath**              | **56.86** |
+| Llama2-70B                | 56.80 |
+| Llama-3-8B                | 56.00 |
+| Mistral-7B                | 52.20 |
+| Gemma-7B                  | 46.40 |
+| DeepSeek-V2-Lite          | 38.21 |
+| gpt-oss-20b               | 36.54 |