lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initialize evaluation protocols and examples; Implement one kind of eval; Update requirements

Browse Source
This commit is contained in:
Timothyxxx
2023-12-12 18:10:55 +08:00
parent 4b3af14b8f
commit 2ca36109b5
8 changed files with 139 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
evaluation_examples/examples/37608790-6147-45d0-9f20-1137bb35703d.json
View File

@@ -18,5 +18,17 @@
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
"evaluator": {
"func": "compare_table(expected, actual)",
"paths": {
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1dxpiUqP_CVvQp5tddxlwO3Cp1BqJ-ZDE&export=download&authuser=0&confirm=t&uuid=ccd204c7-07ce-4fdf-a5d4-a7e4f37b9ce6&at=APZUnTVBs7TgrVrDXpkiU8S7WbQo:1702360836747"
},
"actual": {
"type": "vm_file",
"path": "C:\\Users\\tianbaox\\Desktop\\Employee_Roles_and_Ranks.xlsx"
}
}
}
}

14
evaluation_examples/examples/d681960f-7bc3-4286-9913-a8812ba3261a.json
View File

@@ -18,5 +18,17 @@
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
"evaluator": {
"func": "compare_table(expected, actual)",
"paths": {
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1kfEHJH1n0yCsQp443IIFvdD9uWv0DWMr&export=download&authuser=0&confirm=t&uuid=d9907f65-8d39-4ecc-8747-b4ed7e6011f5&at=APZUnTXpPAnlh5sD6q-R8oQtqL6g:1702362952170"
},
"actual": {
"type": "vm_file",
"path": "C:\\Users\\tianbaox\\Desktop\\Student_Grades_and_Remarks.xlsx"
}
}
}
}

14
evaluation_examples/examples/f9584479-3d0d-4c79-affa-9ad7afdd8850.json
View File

@@ -18,5 +18,17 @@
"related_apps": [
"libreoffice calc"
],
"evaluator": "evaluation_dir"
"evaluator": {
"func": "compare_table(expected, actual)",
"paths": {
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=17f1wZuJPvUEc5at_Fy3c18VFdOk0x7xz&export=download&authuser=0&confirm=t&uuid=6d2edffd-0ce0-426e-9820-8af25b4667f3&at=APZUnTVh7JS85dwZBaV2hytWQgDK:1702361510956"
},
"actual": {
"type": "vm_file",
"path": "C:\\Users\\tianbaox\\Desktop\\Quarterly_Product_Sales_by_Zone.xlsx"
}
}
}
}