Online-Mind2Web

# 运行前 3 个任务
bubench run \
  --agent browser-use \
  --data Online-Mind2Web \
  --mode first_n \
  --count 3

# 运行全部任务
bubench run \
  --agent Agent-TARS \
  --data Online-Mind2Web \
  --mode all \
  --skip-completed

bubench eval --agent browser-use --data Online-Mind2Web --model-id bu-2-0

{
  "task_id": "b7258ee05d75e6c50673a59914db412e_110325",
  "confirmed_task": "Find the store location and hours of the closest Trader Joe's to zip code 90028 and set it as my home store.",
  "website": "https://www.traderjoes.com/",
  "reference_length": 6,
  "level": "medium"
}