Update README.md

README.md

@@ -11,8 +11,19 @@ tags:
 # Lumina-3
 
 Lumina-3 is a Mixture of Experts (MoE) using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing).
-From my testing, it is the best model I have made so far and does well overall for its size; from roleplaying, math, and coding.
-Benchmarks will be coming soon.
+From my testing, it is the best model I have made so far and does well overall for its size; from roleplaying, math, and coding. This model uses a context window of up to 32k.
+
+## 🏆 Open LLM Leaderboard Evaluation Results 
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.53|
+|AI2 Reasoning Challenge (25-Shot)|71.16|
+|HellaSwag (10-Shot)              |87.20|
+|MMLU (5-Shot)                    |65.52|
+|TruthfulQA (0-shot)              |68.25|
+|Winogrande (5-shot)              |82.08|
+|GSM8k (5-shot)                   |72.93|
 
 ## 💻 Usage