Adding Evaluation Results (#1)

- Adding Evaluation Results (c86c22c35ad178ce8e2d4cc8227e3747330ffc50)

README.md

@@ -21,6 +21,101 @@ metrics:
 - character
 library_name: transformers
 pipeline_tag: text-generation
+model-index:
+- name: PathfinderAI
+  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: 37.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      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: 52.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      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: 47.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      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: 19.24
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      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: 20.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      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: 51.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Daemontatox/PathfinderAI
+      name: Open LLM Leaderboard
 ---
 
 ![image](./image.webp)
@@ -125,4 +220,18 @@ Special thanks to:
 
 ---
 
-Experience the **PathfinderAI l**, leveraging its structured reasoning and self-improvement capabilities for any task requiring advanced AI reasoning.
+Experience the **PathfinderAI l**, leveraging its structured reasoning and self-improvement capabilities for any task requiring advanced AI reasoning.
+# [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/Daemontatox__PathfinderAI-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=Daemontatox/PathfinderAI)!
+
+|      Metric       |% Value|
+|-------------------|------:|
+|Avg.               |  38.13|
+|IFEval (0-Shot)    |  37.45|
+|BBH (3-Shot)       |  52.65|
+|MATH Lvl 5 (4-Shot)|  47.58|
+|GPQA (0-shot)      |  19.24|
+|MuSR (0-shot)      |  20.83|
+|MMLU-PRO (5-shot)  |  51.04|
+