Update README.md

README.md

@@ -29,10 +29,10 @@ model-index:
           name: GPQA
           type: open
         metrics:
-          - name: Accuracy (Strict Extraction)
+          - name: Accuracy (Clean Extraction)
             type: accuracy
             value: 0.386
-          - name: Accuracy (Soft Extraction)
+          - name: Accuracy (All Extraction)
             type: accuracy
             value: 0.410
       - task: