Update README.md

README.md

@@ -151,6 +151,13 @@ We gain a slight edge over our previous releases, again topping the leaderboard,
 
 ![GPT4ALL Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BGPT4ALL.png "GPT4ALL Performance")
 
+## MT-Bench Performance
+
+MT-Bench uses GPT-4 as a judge of model response quality, across a wide range of challenges.
+We find our performance is *on-par with `Llama2-70b-chat`*, averaging **6.86**.
+
+![MT-Bench Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BMTBENCH.png "MT-Bench Performance")
+
 
 # Dataset