docs/reports/quick_model_comparison.json

{
  "results": [
    {
      "name": "Qwen2.5-0.5B",
      "score": 7,
      "time": 4.335223197937012,
      "response": ".\n\nOutils: get_game_state(), move_units(unit_ids, target_x, target_y)\n\nCommande: \"Montre-moi l'état du jeu\"\n\nRéponds avec JSON: {{\"tool\": \"nom_outil\", \"args\": {{}}}}. \n\nNote: \"nom_outil\" est le nom de l'outil utilisé pour la commande, \"nom_outil\" est le nom du tool utilisé pour la commande. \"args\" est un dictionnaire contenant"
    },
    {
      "name": "Qwen3-0.6B",
      "score": 7,
      "time": 8.028195858001709,
      "response": "Exemple: {\"tool\": \"get_game_state\", \"args\": {\"unit_ids\": \"1,2,3\", \"target_x\": \"4\", \"target_y\": \"5\"}}\n\nExemple 2: {\"tool\": \"move_units\", \"args\": {\"unit_ids\": \"1,2,3\", \"target_x\": \"4\", \"target_y\": \"5\"}}\n\nExemple 3: {\"tool\": \"get_game_state\", \"args\": {\"unit"
    },
    {
      "name": "Gemma-3-1B",
      "score": 7,
      "time": 8.582704782485962,
      "response": "```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_"
    }
  ],
  "ranking": [
    {
      "name": "Qwen2.5-0.5B",
      "score": 7,
      "time": 4.335223197937012,
      "response": ".\n\nOutils: get_game_state(), move_units(unit_ids, target_x, target_y)\n\nCommande: \"Montre-moi l'état du jeu\"\n\nRéponds avec JSON: {{\"tool\": \"nom_outil\", \"args\": {{}}}}. \n\nNote: \"nom_outil\" est le nom de l'outil utilisé pour la commande, \"nom_outil\" est le nom du tool utilisé pour la commande. \"args\" est un dictionnaire contenant"
    },
    {
      "name": "Qwen3-0.6B",
      "score": 7,
      "time": 8.028195858001709,
      "response": "Exemple: {\"tool\": \"get_game_state\", \"args\": {\"unit_ids\": \"1,2,3\", \"target_x\": \"4\", \"target_y\": \"5\"}}\n\nExemple 2: {\"tool\": \"move_units\", \"args\": {\"unit_ids\": \"1,2,3\", \"target_x\": \"4\", \"target_y\": \"5\"}}\n\nExemple 3: {\"tool\": \"get_game_state\", \"args\": {\"unit"
    },
    {
      "name": "Gemma-3-1B",
      "score": 7,
      "time": 8.582704782485962,
      "response": "```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_state\", \"args\": {\"map\": \"map_name\"}}}}\n```\n\n```json\n{{\"tool\": \"get_game_"
    }
  ],
  "best_model": "Qwen2.5-0.5B"
}