Update README.md

README.md

@@ -49,13 +49,13 @@ Function Calling Benchmark: https://huggingface.co/datasets/phamhai/Vietnamese-F
 
 | Model              | Model size | Function name Acc (%) | Exact Match Acc (%)
 | ------------ | ------------------ | ---------- | --------- |
-| [phamhai/Llama-3.2-3B-Instruct-Frog](https://huggingface.co/phamhai/Llama-3.2-3B-Instruct-Frog)            | ~3B        | 95.79    | 47.78  |
+| [phamhai/Llama-3.2-3B-Instruct-Frog](https://huggingface.co/phamhai/Llama-3.2-3B-Instruct-Frog)            | ~3B        | 95.79    | 51.05  |
 | [Gemini-1.5-Pro](https://deepmind.google/technologies/gemini/pro/)         | ---        | 96.96    | 55.16     |
 | [Gemini-1.5-Flash](https://deepmind.google/technologies/gemini/flash/)         | ---        | 97.10    | 51.64     |
 | [Gemini-1.5-Flash-8B](https://deepmind.google/technologies/gemini/flash/)         | ---        | 97.38    | 64.75     |
 | [gpt-4o-2024-08-06](https://platform.openai.com/docs/models#gpt-4o)         | ---        | 94.38    | 52.88     |
 | [arcee-ai/Arcee-VyLinh](https://huggingface.co/arcee-ai/Arcee-VyLinh)     | ~3B        |     |     | 
-| [phamhai/Llama-3.2-3B-Instruct-Frog-Pro](https://huggingface.co/phamhai/Llama-3.2-3B-Instruct-Frog-Pro)            | ~3B        | 98.12    | 53.11  |
+| [phamhai/Llama-3.2-3B-Instruct-Frog-Pro](https://huggingface.co/phamhai/Llama-3.2-3B-Instruct-Frog-Pro)            | ~3B        | 98.12    | 56.38  |
 
 <p align="left"> Table 1. Vietnamese Function Calling Benchmark </p>