Add model-index metadata for benchmark results

This PR adds machine-readable evaluation metadata to the model card using the `model-index` format.

## What This Adds

Structured YAML metadata for 7 benchmark(s) from the README:

- MATH-500: 98.1
- AIME24: 90.8
- AIME25: 88.0
- LCB: 69.3
- GPQA: 74.4
- HLE: 14.6
- MMLU-Pro: 81.9

## Why This Helps

Adding structured benchmark metadata enables:

1. **Automatic Leaderboard Inclusion** - Model appears on Hugging Face leaderboards and Papers with Code
2. **Better Discoverability** - Users can search/filter models by benchmark scores
3. **Machine-Readable Data** - Tools and APIs can query model performance programmatically

## What Doesn't Change

- ✅ Existing README content stays the same
- ✅ Markdown benchmark tables remain unchanged
- ✅ Only adds metadata to the YAML frontmatter

Thank you for open-sourcing INTELLECT-3! This contribution helps the community compare and discover your work.

README.md

@@ -14,6 +14,39 @@ language:
 base_model:
 - zai-org/GLM-4.5-Air-Base
 pipeline_tag: text-generation
+model-index:
+- name: INTELLECT-3
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Benchmarks
+      type: benchmark
+    metrics:
+    - name: MATH-500
+      type: math_500
+      value: 98.1
+    - name: AIME24
+      type: aime24
+      value: 90.8
+    - name: AIME25
+      type: aime25
+      value: 88.0
+    - name: LCB
+      type: lcb
+      value: 69.3
+    - name: GPQA
+      type: gpqa
+      value: 74.4
+    - name: HLE
+      type: hle
+      value: 14.6
+    - name: MMLU-Pro
+      type: mmlu_pro
+      value: 81.9
+    source:
+      name: Model README
+      url: https://huggingface.co/PrimeIntellect/INTELLECT-3
 ---
 
 # INTELLECT-3