openhands
Fix category cost calculation - add category-level aggregation
5e9c3b9
{
"suite_config": {
"name": "openhands-index",
"version": "1.0.0-dev1",
"splits": [
{
"name": "test",
"tasks": [
{
"name": "swe-bench",
"tags": [
"Overall",
"Bug Fixing",
"swe-bench"
]
},
{
"name": "swe-bench-multimodal",
"tags": [
"Overall",
"Bug Fixing",
"swe-bench-multimodal"
]
},
{
"name": "commit0",
"tags": [
"Overall",
"App Creation",
"commit0"
]
},
{
"name": "multi-swe-bench",
"tags": [
"Overall",
"Frontend Development",
"multi-swe-bench"
]
},
{
"name": "swt-bench",
"tags": [
"Overall",
"Test Generation",
"swt-bench"
]
},
{
"name": "gaia",
"tags": [
"Overall",
"Information Gathering",
"gaia"
]
}
]
},
{
"name": "validation",
"tasks": [
{
"name": "swe-bench",
"tags": [
"Overall",
"Bug Fixing",
"swe-bench"
]
},
{
"name": "swe-bench-multimodal",
"tags": [
"Overall",
"Bug Fixing",
"swe-bench-multimodal"
]
},
{
"name": "commit0",
"tags": [
"Overall",
"App Creation",
"commit0"
]
},
{
"name": "multi-swe-bench",
"tags": [
"Overall",
"Frontend Development",
"multi-swe-bench"
]
},
{
"name": "swt-bench",
"tags": [
"Overall",
"Test Generation",
"swt-bench"
]
},
{
"name": "gaia",
"tags": [
"Overall",
"Information Gathering",
"gaia"
]
}
]
}
]
}
}