Update README.md

README.md

@@ -8,7 +8,11 @@ pipeline_tag: text-generation
 **Typhoon2-Qwen2.5-7B** is a pretrained only Thai 🇹🇭 large language model with 7 billion parameters, and it is based on Qwen2.5-7B.
 
 
-[TODO add one image and table result]
+| Model                 | ThaiExam | ONET   | IC        | A-Level   | TGAT      | TPAT      | M3Exam    | Math       | Science    | Social     | Thai       |
+|------------------------|----------|--------|-----------|-----------|-----------|-----------|-----------|------------|------------|------------|------------|
+| **Typhoon2 Qwen2.5 base** | **58.86%** | **58.64%** | 65.26%    | **55.11%** | 66.15%    | 49.13%    | **59.90%** | 42.98%     | **59.42%** | **75.62%** | **61.59%** |
+| **Qwen2.5 7b**         | 55.74%   | 51.23% | **60.00%** | 41.73%    | **72.30%** | **53.44%** | 55.65%    | **46.15%** | 54.10%     | 66.54%     | 55.82%     |
+| **Typhoon1.5 base**   | 48.82%   | 41.35% | 41.05%    | 40.94%    | 70.76%    | 50.00%    | 43.88%    | 22.62%     | 43.47%     | 62.81%     | 46.63%     |
 
 For release post, please see our [blog](...).