Adding Evaluation Results (#1)

- Adding Evaluation Results (2ede5cf4edc32a8c00d0e07bbf31dbf74ca2c969)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,5 +1,100 @@
 ---
 license: apache-2.0
+model-index:
+- name: ArliAI-RPMax-12B-v1.1
+  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: 53.49
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      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: 24.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      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: 9.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      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: 4.25
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      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: 5.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      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: 26.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ArliAI/ArliAI-RPMax-12B-v1.1
+      name: Open LLM Leaderboard
 ---
 # ArliAI-RPMax-12B-v1.1
 =====================================
@@ -49,3 +144,17 @@ The model is available in quantized formats:
 ## Suggested Prompt Format
 
 Mistral Instruct Prompt Format
+
+# [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_ArliAI__ArliAI-RPMax-12B-v1.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.64|
+|IFEval (0-Shot)    |53.49|
+|BBH (3-Shot)       |24.81|
+|MATH Lvl 5 (4-Shot)| 9.21|
+|GPQA (0-shot)      | 4.25|
+|MuSR (0-shot)      | 5.56|
+|MMLU-PRO (5-shot)  |26.49|
+