Update README.md

README.md

@@ -30,10 +30,10 @@ model-index:
           type: text-generation
         dataset:
           name: ai2_arc
-          type: ai2_arc
+          type: arc
         metrics:
-          - name: AI2 Reasoning Challenge (25-Shot)
-            type: AI2 Reasoning Challenge (25-Shot)
+          - name: pass@1
+            type: pass@1
             value: 35.92
         source:
           name: Open LLM Leaderboard
@@ -44,8 +44,8 @@ model-index:
           name: hellaswag
           type: hellaswag
         metrics:
-          - name: HellaSwag - Commonsense Inference (10-shot)
-            type: HellaSwag - Commonsense Inference (10-shot)
+          - name: pass@1
+            type: pass@1
             value: 60.03
         source:
           name: Open LLM Leaderboard
@@ -56,8 +56,8 @@ model-index:
           name: truthful_qa
           type: truthful_qa
         metrics:
-          - name: TruthfulQA (0-shot)
-            type: TruthfulQA (0-shot)
+          - name: pass@1
+            type: pass@1
             value: 39.17
         source:
           name: Open LLM Leaderboard
@@ -68,8 +68,8 @@ model-index:
           name: winogrande
           type: winogrande
         metrics:
-          - name: Winogrande (5-shot)
-            type: Winogrande - Adversarial Winograd Schema Challenge (5-shot)
+          - name: pass@1
+            type: pass@1
             value: 61.09
         source:
           name: Open LLM Leaderboard