diff --git a/wolf/leaderboard.py b/wolf/leaderboard.py
new file mode 100644
index 0000000..4684453
--- /dev/null
+++ b/wolf/leaderboard.py
@@ -0,0 +1,77 @@
+import logging
+import json
+from pathlib import Path
+from typing import Dict, Any, List, Optional
+from datetime import datetime
+
+class Leaderboard:
+    """
+    Leaderboard for Wolf.
+    """
+    def __init__(self, storage_path=None):
+        self.storage_path = Path(storage_path or Path.home() / ".hermes" / "wolf" / "leaderboard.json")
+        self.storage_path.parent.mkdir(parents=True, exist_ok=True)
+        self.data = self._load()
+
+    def _load(self):
+        if not self.storage_path.exists():
+            return {"models": {}, "history": []}
+        with open(self.storage_path, 'r') as f:
+            return json.load(f)
+
+    def _save(self):
+        with open(self.storage_path, 'w') as f:
+            json.dump(self.data, f, indent=2)
+
+    def record_score(self, model_name, provider, task_id, score_data):
+        """
+        Record a score for a model on a specific task.
+        """
+        logging.info(f"Recording score for model {model_name}: {score_data['total_score']}")
+        
+        # 1. Update model stats
+        if model_name not in self.data["models"]:
+            self.data["models"][model_name] = {
+                "provider": provider,
+                "total_tasks": 0,
+                "average_score": 0,
+                "scores": [],
+                "serverless_ready": False
+            }
+        
+        model_stats = self.data["models"][model_name]
+        model_stats["total_tasks"] += 1
+        model_stats["scores"].append(score_data["total_score"])
+        model_stats["average_score"] = sum(model_stats["scores"]) / len(model_stats["scores"])
+        
+        # 2. Check for deployment readiness (e.g., average score > 80 after 5 tasks)
+        if model_stats["total_tasks"] >= 5 and model_stats["average_score"] >= 80:
+            model_stats["serverless_ready"] = True
+            logging.info(f"Model {model_name} is now serverless-ready!")
+        
+        # 3. Record history
+        self.data["history"].append({
+            "timestamp": datetime.now().isoformat(),
+            "model_name": model_name,
+            "provider": provider,
+            "task_id": task_id,
+            "score": score_data
+        })
+        
+        self._save()
+
+    def get_rankings(self):
+        """
+        Get model rankings sorted by average score.
+        """
+        rankings = []
+        for model_name, stats in self.data["models"].items():
+            rankings.append({
+                "model_name": model_name,
+                "provider": stats["provider"],
+                "average_score": stats["average_score"],
+                "total_tasks": stats["total_tasks"],
+                "serverless_ready": stats["serverless_ready"]
+            })
+        
+        return sorted(rankings, key=lambda x: x["average_score"], reverse=True)