Update README.md

README.md

@@ -263,6 +263,8 @@ Data Labeling for Evaluation Datasets:
 ## Evaluation Results
 We evaluate the model using temperature=`0.6`, top_p=`0.95`, and 64k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate.
 
+All evaluations were done using [NeMo-Skills](https://github.com/NVIDIA/NeMo-Skills). We published a [tutorial](https://nvidia.github.io/NeMo-Skills/tutorials/2025/08/15/reproducing-llama-nemotron-super-49b-v15-evals/) with all details necessary to reproduce our evaluation results.
+
 ### MATH500
 
 | Reasoning Mode | pass@1 (avg. over 4 runs) |