add link to flexeval evaluation manifest

Updated the Evaluation section to include a link to the flexeval manifest repository.

README.md

@@ -20,6 +20,10 @@ This repository provides Japanese language models trained by [SB Intuitions](htt
 
 ## Evaluation in Japanese and English Tasks
 
+For detailed evaluation protocols, judge settings, prompt templates, and reproducible execution scripts,
+please refer to
+the [flexeval evaluation manifest](https://github.com/sbintuitions/flexeval/tree/main/examples/sarashina_2_2_evaluation) (in Japanese).
+
 | Model                                                                                             | Elyza-tasks-100 | Japanese MT Bench | English MT Bench |
 | ------------------------------------------------------------------------------------------------- | --------------- | ----------------- | ---------------- |
 | [Qwen/Qwen2.5-0.5B-instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)                   | 1.53            | 2.95              | 4.98             |