Adding Evaluation Results (#1)

- Adding Evaluation Results (f8073219890c4feae228a7cf435ce67cc92652ed)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,7 +1,102 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+model-index:
+- name: Mistral7B-PairRM-SPPO-ExPO
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 36.73
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 13.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      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: 8.66
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      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: 17.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chujiezheng/Mistral7B-PairRM-SPPO-ExPO
+      name: Open LLM Leaderboard
 ---
 
 # Mistral7B-PairRM-SPPO-ExPO
@@ -48,3 +143,17 @@ Evaluation results on the **MT-Bench** benchmark (you can find the evaluation ou
 | `allenai/tulu-2-dpo-13b`             | 7.00     | **7.26** |
 | `allenai/tulu-2-dpo-70b`             | 7.79     | **8.03** |
 
+
+# [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/details_chujiezheng__Mistral7B-PairRM-SPPO-ExPO)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |13.47|
+|IFEval (0-Shot)    |36.73|
+|BBH (3-Shot)       |13.68|
+|MATH Lvl 5 (4-Shot)| 0.91|
+|GPQA (0-shot)      | 3.58|
+|MuSR (0-shot)      | 8.66|
+|MMLU-PRO (5-shot)  |17.24|
+