Added Evaluation Benchmarks to Metadata

README.md

@@ -4,6 +4,60 @@ library_name: transformers
 base_model:
   - deepseek-ai/DeepSeek-V3.2-Exp-Base
 base_model_relation: finetune
+model-index:
+- name: DeepSeek-V3.2-Exp
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Benchmarks
+      type: benchmark
+    metrics:
+    - name: MMLU-Pro
+      type: mmlu-pro
+      value: 85.0
+    - name: GPQA-Diamond
+      type: gpqa-diamond
+      value: 79.9
+    - name: Humanity's Last Exam
+      type: humanity's_last_exam
+      value: 19.8
+    - name: LiveCodeBench
+      type: livecodebench
+      value: 74.1
+    - name: AIME 2025
+      type: aime_2025
+      value: 89.3
+    - name: HMMT 2025
+      type: hmmt_2025
+      value: 83.6
+    - name: Codeforces
+      type: codeforces
+      value: 2121.0
+    - name: Aider-Polyglot
+      type: aider-polyglot
+      value: 74.5
+    - name: BrowseComp
+      type: browsecomp
+      value: 40.1
+    - name: BrowseComp-zh
+      type: browsecomp-zh
+      value: 47.9
+    - name: SimpleQA
+      type: simpleqa
+      value: 97.1
+    - name: SWE Verified
+      type: swe_verified
+      value: 67.8
+    - name: SWE-bench Multilingual
+      type: swe-bench_multilingual
+      value: 57.9
+    - name: Terminal-bench
+      type: terminal-bench
+      value: 37.7
+    source:
+      name: Model README
+      url: https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
 ---
 # DeepSeek-V3.2-Exp