Add model-index with benchmark evaluations

Added structured evaluation results from benchmark image:
- SimpleQA: 8.90
- MUSR: 63.49
- MMLU (Zero Shot): 84.95
- Math-500: 92.10
- GPQA-Diamond: 58.55
- BFCL V3: 59.67

This enables the model to appear in leaderboards and makes it easier to compare with other models.

README.md

@@ -15,6 +15,36 @@ language:
 library_name: transformers
 base_model:
 - arcee-ai/Trinity-Mini-Base
+model-index:
+- name: Trinity-Mini
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Benchmarks
+      type: benchmark
+    metrics:
+    - name: SimpleQA
+      type: simpleqa
+      value: 8.9
+    - name: MUSR
+      type: musr
+      value: 63.49
+    - name: MMLU (Zero Shot)
+      type: mmlu_zero_shot
+      value: 84.95
+    - name: Math-500
+      type: math_500
+      value: 92.1
+    - name: GPQA-Diamond
+      type: gpqa_diamond
+      value: 58.55
+    - name: BFCL V3
+      type: bfcl_v3
+      value: 59.67
+    source:
+      name: Model README
+      url: https://huggingface.co/arcee-ai/Trinity-Mini
 ---
 <div align="center">
   <picture>