{
  "schema": "rlebench/family-overview/1",
  "seed": 0,
  "token_accounting": "Input includes cached input; output includes reasoning output. Total is input plus output. Incomplete usage is a lower bound from available provider records.",
  "families": [
    {
      "family": "task01",
      "label": "Task01 \u00b7 RoboCasa",
      "tasks": 8,
      "valid_results": 8,
      "native_successes": 1,
      "success_rate": 0.125,
      "usage_complete_tasks": 8,
      "usage_complete": true,
      "token_counts_are_lower_bounds": false,
      "tokens": {
        "input_tokens": 90216131,
        "output_tokens": 132901,
        "cached_input_tokens": 88383744,
        "reasoning_output_tokens": 41238,
        "total_tokens": 90349032
      },
      "kinex_versions": {
        "0.9.0": 8
      },
      "evaluated_tasks": 8,
      "evaluated_native_successes": 1,
      "interrupted_tasks": 0
    },
    {
      "family": "task02",
      "label": "Task02 \u00b7 LIBERO",
      "tasks": 2,
      "valid_results": 2,
      "native_successes": 2,
      "success_rate": 1.0,
      "usage_complete_tasks": 2,
      "usage_complete": true,
      "token_counts_are_lower_bounds": false,
      "tokens": {
        "input_tokens": 13857575,
        "output_tokens": 29068,
        "cached_input_tokens": 13547520,
        "reasoning_output_tokens": 12367,
        "total_tokens": 13886643
      },
      "kinex_versions": {
        "0.8.0": 2
      },
      "evaluated_tasks": 2,
      "evaluated_native_successes": 2,
      "interrupted_tasks": 0
    },
    {
      "family": "task03",
      "label": "Task03 \u00b7 RoboTwin",
      "tasks": 4,
      "valid_results": 4,
      "native_successes": 4,
      "success_rate": 1.0,
      "usage_complete_tasks": 4,
      "usage_complete": true,
      "token_counts_are_lower_bounds": false,
      "tokens": {
        "input_tokens": 5669649,
        "output_tokens": 22280,
        "cached_input_tokens": 5394944,
        "reasoning_output_tokens": 6047,
        "total_tokens": 5691929
      },
      "kinex_versions": {
        "0.8.2": 2,
        "0.9.0": 2
      },
      "evaluated_tasks": 4,
      "evaluated_native_successes": 4,
      "interrupted_tasks": 0
    },
    {
      "family": "task04",
      "label": "Task04 \u00b7 RoboDojo",
      "tasks": 10,
      "valid_results": 10,
      "native_successes": 7,
      "success_rate": 0.7,
      "usage_complete_tasks": 10,
      "usage_complete": true,
      "token_counts_are_lower_bounds": false,
      "tokens": {
        "input_tokens": 96905594,
        "output_tokens": 193344,
        "cached_input_tokens": 94595072,
        "reasoning_output_tokens": 84902,
        "total_tokens": 97098938
      },
      "kinex_versions": {
        "0.8.2": 4,
        "0.9.0": 6
      },
      "evaluated_tasks": 10,
      "evaluated_native_successes": 7,
      "interrupted_tasks": 0
    },
    {
      "family": "task05",
      "label": "Task05 \u00b7 BEHAVIOR",
      "tasks": 8,
      "valid_results": 8,
      "native_successes": 1,
      "success_rate": 0.125,
      "usage_complete_tasks": 8,
      "usage_complete": true,
      "token_counts_are_lower_bounds": false,
      "tokens": {
        "input_tokens": 177464914,
        "output_tokens": 262742,
        "cached_input_tokens": 174090240,
        "reasoning_output_tokens": 127330,
        "total_tokens": 177727656
      },
      "kinex_versions": {
        "0.9.0": 2,
        "0.8.2": 6
      },
      "evaluated_tasks": 8,
      "evaluated_native_successes": 1,
      "interrupted_tasks": 0
    }
  ]
}
