xiangyi-li
/
OS-World
mirrored a few seconds ago
0
Benchmark CardFiles and versionsLeaderboard
yuanmengqifeat: standardize configuration fields across all evaluation examples - Add `fixed_ip` field to all 369 JSON files in examples directory - Set to `true` for 8 files listed in google_chrome.json multi_apps - Set to `false` for remaining 361 files - Add `possibility_of_env_change` field to 363 JSON files missing this field - Set to "low" for newly added fields - Preserve existing values (4 medium, 2 high) for 6 files that already had this field This ensures consistent configuration schema across all evaluation examples while maintaining backward compatibility with existing settings. e433f35
Raw
-
{
  "id": "58d3eeeb-e9d0-499f-962e-fd0db2a744d8",
  "snapshot": "gimp",
  "instruction": "Based on the image above, translate the hidden audio conversation into French.",
  "source": "",
  "config": [
    {
      "type": "download",
      "parameters": {
        "files": [
          {
            "url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/gimp/58d3eeeb-e9d0-499f-962e-fd0db2a744d8/heron.jpeg",
            "path": "/home/user/Desktop/heron.jpeg"
          }
        ]
      }
    },
    {
      "type": "launch",
      "parameters": {
        "command": [
          "gimp",
          "/home/user/Desktop/heron.jpeg"
        ]
      }
    }
  ],
  "trajectory": "trajectories/",
  "related_apps": [
    "gimp"
  ],
  "evaluator": {
    "func": "infeasible"
  },
  "proxy": false,
  "fixed_ip": false,
  "possibility_of_env_change": "low"
}