Update README.md

README.md

@@ -161,7 +161,14 @@ We briefly compare SeaLLMs-v3-1.5B-Chat with models of similar sizes with the M3
 
 [M3Exam](https://arxiv.org/abs/2306.05179) consists of local exam questions collected from each country. It reflects the model's world knowledge (e.g., with language or social science subjects) and reasoning abilities (e.g., with mathematics or natural science subjects).
 
-[[place holder]]
+| Model                    | en   | zh   | id   | th   | vi   | avg  | avg_sea |
+|--------------------------|------|------|------|------|------|------|---------|
+| gemma-2b-it              | 44.1 | 37.4 | 31.5 | 28.2 | 35.8 | 35.4 | 31.8    |
+| Sailor-1.8B-Chat         | 43.8 | 35.9 | 34.2 | 32.3 | 37.5 | 36.7 | 34.7    |
+| Sailor-4B-Chat           | 54.1 | 48.1 | 40.7 | 35.6 | 42.5 | 44.2 | 39.6    |
+| Qwen2-1.5B-Instruct      | 63.4 | 75.3 | 41.2 | 41.2 | 47.2 | 53.7 | 43.2    |
+| **SeaLLMs-v3-1.5B-Chat** | 61.9 | 74.2 | 43.2 | 42.4 | 48.7 | 54.1 | 44.7    |
+
 
 
 ## Acknowledgement to Our Linguists