Adding Evaluation Results

This is an automated PR created with [this space](https://huggingface.co./spaces/T145/open-llm-leaderboard-results-to-modelcard)!

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

Please report any issues here: https://huggingface.co./spaces/T145/open-llm-leaderboard-results-to-modelcard/discussions

README.md

@@ -10,6 +10,105 @@ tags:
 datasets:
 - NovaSky-AI/Sky-T1_data_17k
 license: mit
+model-index:
+- name: phi4-qwq-sky-t1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 4.6
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 52.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 39.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 19.35
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 21.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 47.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=benhaotang%2Fphi4-qwq-sky-t1
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -78,4 +177,18 @@ parameters:
   normalize: false
   int8_mask: true
 dtype: float16
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/benhaotang__phi4-qwq-sky-t1-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=benhaotang%2Fphi4-qwq-sky-t1&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    30.78|
+|IFEval (0-Shot)    |     4.60|
+|BBH (3-Shot)       |    52.61|
+|MATH Lvl 5 (4-Shot)|    39.58|
+|GPQA (0-shot)      |    19.35|
+|MuSR (0-shot)      |    21.38|
+|MMLU-PRO (5-shot)  |    47.16|
+