Update README.md

README.md

@@ -153,11 +153,10 @@ Here, all benchmarks were done 0-shot, on the exception of NQ Open and TriviaQA
 If we try to replicate OpenLLM Leaderboard results on available Serbian datasets (running an appropriate amount of shots instead of 0), we get:
 |         | ARC   | Hellaswag | Winogrande | TruthfulQA | Avg.  |
 |---------|-------|-----------|------------|------------|-------|
-| Tito-7B | 47.27 |     -     |   69.93    |            |   -   |
-| YugoGPT | 44.03 |     -     |   70.64    |            |   -   |
-| [Perucac-7B](https://huggingface.co/Stopwolf/Perucac-7B-slerp)  | 49.74 |   -   | 71.98 | 56.03 |   -   |
-| Llama3-8B | 42.24 |    -    |   61.25    |            |   -   |
-
+| Tito-7B | 47.27 |     -     |   69.93    |  **57.48** | 58.23 |
+| YugoGPT | 44.03 |     -     |   70.64    |    48.06   | 54.24 |
+| [Perucac-7B](https://huggingface.co/Stopwolf/Perucac-7B-slerp)  | **49.74** |   -   | **71.98** | 56.03 | **59.25** |
+| Llama3-8B | 42.24 |    -    |   61.25    |     51.08  | 51.52 |
 
 
 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)