Update leaderboard.py

leaderboard.py

@@ -71,3 +71,96 @@ def create_backup():
 def start_backup_thread():
     backup_thread = threading.Thread(target=create_backup, daemon=True)
     backup_thread.start()
+
+
+def get_human_readable_name(model_name: str) -> str:
+    model_dict = dict(arena_config.APPROVED_MODELS)
+    return model_dict.get(model_name, model_name)
+
+def get_leaderboard():
+    battle_results = get_current_leaderboard()
+    
+    # Calculate scores for each model
+    for model, results in battle_results.items():
+        total_battles = results["wins"] + results["losses"]
+        if total_battles > 0:
+            win_rate = results["wins"] / total_battles
+            results["score"] = win_rate * (1 - 1 / (total_battles + 1))
+        else:
+            results["score"] = 0
+
+    # Sort results by score, then by total battles
+    sorted_results = sorted(
+        battle_results.items(), 
+        key=lambda x: (x[1]["score"], x[1]["wins"] + x[1]["losses"]), 
+        reverse=True
+    )
+
+    leaderboard = """
+    <style>
+        .leaderboard-table {
+            width: 100%;
+            border-collapse: collapse;
+            font-family: Arial, sans-serif;
+        }
+        .leaderboard-table th, .leaderboard-table td {
+            border: 1px solid #ddd;
+            padding: 8px;
+            text-align: left;
+        }
+        .leaderboard-table th {
+            background-color: rgba(255, 255, 255, 0.1);
+            font-weight: bold;
+        }
+        .rank-column {
+            width: 60px;
+            text-align: center;
+        }
+        .opponent-details {
+            font-size: 0.9em;
+            color: #888;
+        }
+    </style>
+    <table class='leaderboard-table'>
+    <tr>
+        <th class='rank-column'>Rank</th>
+        <th>Model</th>
+        <th>Score</th>
+        <th>Wins</th>
+        <th>Losses</th>
+        <th>Win Rate</th>
+        <th>Total Battles</th>
+        <th>Top Rival</th>
+        <th>Toughest Opponent</th>
+    </tr>
+    """
+    
+    for index, (model, results) in enumerate(sorted_results, start=1):
+        total_battles = results["wins"] + results["losses"]
+        win_rate = (results["wins"] / total_battles * 100) if total_battles > 0 else 0
+        
+        rank_display = {1: "🥇", 2: "🥈", 3: "🥉", 18: "😞", 19: "😰", 20: "😭"}.get(index, f"{index}")
+        
+        top_rival = max(results["opponents"].items(), key=lambda x: x[1]["wins"], default=(None, {"wins": 0}))
+        top_rival_name = get_human_readable_name(top_rival[0]) if top_rival[0] else "N/A"
+        top_rival_wins = top_rival[1]["wins"]
+        
+        toughest_opponent = max(results["opponents"].items(), key=lambda x: x[1]["losses"], default=(None, {"losses": 0}))
+        toughest_opponent_name = get_human_readable_name(toughest_opponent[0]) if toughest_opponent[0] else "N/A"
+        toughest_opponent_losses = toughest_opponent[1]["losses"]
+        
+        leaderboard += f"""
+        <tr>
+            <td class='rank-column'>{rank_display}</td>
+            <td>{get_human_readable_name(model)}</td>
+            <td>{results['score']:.4f}</td>
+            <td>{results['wins']}</td>
+            <td>{results['losses']}</td>
+            <td>{win_rate:.2f}%</td>
+            <td>{total_battles}</td>
+            <td class='opponent-details'>{top_rival_name} (W: {top_rival_wins})</td>
+            <td class='opponent-details'>{toughest_opponent_name} (L: {toughest_opponent_losses})</td>
+        </tr>
+        """
+    leaderboard += "</table>"
+    return leaderboard