Update README.md

README.md

@@ -45,8 +45,8 @@ model-index:
           type: MT-bench
           name: MT-bench
         metrics:
-          - type: GPT4 Judge
-            value: 8.36
+          - type: GP4-4 as Judge
+            value: 7.36
             verified: false
 ---
 
@@ -59,14 +59,6 @@ The model is the result of further post-training [mistralai/Mistral-7B-Instruct-
 
 The model was post-trained (freeze tuned & DPO) on a proprietary dataset consisting of diverse function calling, chat, and instruct data.
 
-## Evaluation
-
-| Model                              | Function Calling | MMLU  | GPQA  | GSM-8K | MATH  | MT-bench |
-|------------------------------------|------------------|-------|-------|--------|-------|----------|
-| Mistral 7B Instruct v0.2           | -                | 59.27 | 27.68 | 43.21  | 10.30 | 7.50     |
-| Rubra Enhanced Mistral 7B Instruct v0.2 | 69.28%           | 58.90 | 29.91 | 34.12  | 8.36  | 7.36     |
-
-
 ## How to use
 
 You can use the model with the Hugging Face `transformers` and the rubra library [rubra-tools](https://github.com/rubra-ai/rubra-tools) as follows: