Update README.md

README.md

@@ -39,7 +39,7 @@ Evaluated on [`LocalDoc/en_az_translate_benchmark`](https://huggingface.co/datas
 | Qwen3.6-35B-A3B                  |     60.39 |     33.57 |     91.23 |
 | NLLB-200-3.3B (base, zero-shot)  |     59.03 |     31.76 |     89.86 |
 
-Fine-tuning improved the base NLLB-3.3B by **+10.97 chrF++** (59.03 → 69.30) and **+2.89 COMET-DA** (89.86 → 92.75). The result surpasses Google Translate, DeepSeek-V4-Pro, GPT-4.1, Gemma-3-31B, and Qwen-35B, and comes within 0.8 chrF++ of GPT-5.4-mini and Gemini-2.5-flash.
+Fine-tuning improved the base NLLB-3.3B by **+10.97 chrF++** (59.03 → 70.00) and **+2.89 COMET-DA** (89.86 → 92.75). The result surpasses Google Translate, DeepSeek-V4-Pro, GPT-4.1, Gemma-3-31B, and Qwen-35B, and comes within 0.8 chrF++ of GPT-5.4-mini and Gemini-2.5-flash.
 
 ## Example Translations