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

Merge remote-tracking branch 'upstream/main'

Browse Source
This commit is contained in:
yuanmengqi
2025-06-30 08:20:45 +00:00
parent ea51f5264a 30138c5db1
commit b48c69a2fb
21 changed files with 1020 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
evaluation_examples/examples/libreoffice_writer/4bcb1253-a636-4df4-8cb0-a35c04dfef31.json
View File

@@ -27,17 +27,57 @@
"libreoffice_writer"
],
"evaluator": {
"func": "compare_pdfs",
"expected": {
"func": [
"compare_pdfs",
"compare_pdfs",
"compare_pdfs",
"compare_pdfs"
],
"conj": "or",
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/4bcb1253-a636-4df4-8cb0-a35c04dfef31/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_Gold_1.pdf"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/4bcb1253-a636-4df4-8cb0-a35c04dfef31/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_Gold_2.pdf"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/4bcb1253-a636-4df4-8cb0-a35c04dfef31/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_Gold.pdf"
"dest": "Constitution_Template_With_Guidelines_Gold_3.pdf"
},
"result": {
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/4bcb1253-a636-4df4-8cb0-a35c04dfef31/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_Gold_4.pdf"
}
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines.pdf"
}
"dest": "Constitution_Template_With_Guidelines_1.pdf"
},
{
"type": "vm_file",
"path": "/home/user/Documents/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_2.pdf"
},
{
"type": "vm_file",
"path": "/home/user/Downloads/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_3.pdf"
},
{
"type": "vm_file",
"path": "/home/user/View_Person_Organizational_Summary.pdf",
"dest": "Constitution_Template_With_Guidelines_4.pdf"
}
]
},
"proxy": false
}

6
evaluation_examples/examples/libreoffice_writer/6ada715d-3aae-4a32-a6a7-429b2e43fb93.json
View File

@@ -38,7 +38,7 @@
"command": [
"python",
"-c",
"import pyautogui; import time; time.sleep(5); pyautogui.press(\"down\", presses=8, interval=0.01); time.sleep(1); pyautogui.scroll(-2)"
"import pyautogui; import time; time.sleep(15); pyautogui.press(\"down\", presses=8, interval=0.01); time.sleep(1); pyautogui.scroll(-2)"
]
}
}
@@ -68,12 +68,12 @@
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); pyautogui.press('down'); time.sleep(0.5); pyautogui.press('enter');"
"import pyautogui; import time; time.sleep(1); pyautogui.hotkey('ctrl', 's'); time.sleep(3);"
]
}
}
],
"func": "compare_contains_image",
"func": "compare_docx_images",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/Viewing_Your_Class_Schedule_and_Textbooks.docx",

14
evaluation_examples/examples/libreoffice_writer/6f81754e-285d-4ce0-b59e-af7edb02d108.json
View File

@@ -52,7 +52,7 @@
}
}
],
"func": "compare_docx_lines",
"func": "compare_unique_train_records",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/HK_train_record.docx",
@@ -60,8 +60,16 @@
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/6f81754e-285d-4ce0-b59e-af7edb02d108/HK_train_record_Gold.docx",
"dest": "HK_train_record_Gold.docx"
"path": [
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/6f81754e-285d-4ce0-b59e-af7edb02d108/HK_train_record_Gold.docx",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/6f81754e-285d-4ce0-b59e-af7edb02d108/HK_train_record.docx"
],
"dest": [
"HK_train_record_Gold.docx",
"HK_train_record_Original.docx"
],
"multi": true,
"gives": [0, 1]
}
},
"proxy": false

65
evaluation_examples/examples/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48.json
View File

@@ -52,20 +52,57 @@
}
}
],
"func": "compare_docx_files",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
},
"options": {
"ignore_blanks": false
}
"func": [
"compare_docx_files",
"compare_docx_files",
"compare_docx_files"
],
"conj": "or",
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_1.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_1.docx"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_2.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_2.docx"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_3.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_3.docx"
}
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
}
],
"options": [
{
"ignore_blanks": false
},
{
"ignore_blanks": false
},
{
"ignore_blanks": false
}
]
},
"proxy": false
}

42
evaluation_examples/examples/libreoffice_writer/936321ce-5236-426a-9a20-e0e3c5dc536f.json
View File

@@ -47,22 +47,40 @@
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(2); "
]
}
}
],
"func": "compare_docx_tables",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/936321ce-5236-426a-9a20-e0e3c5dc536f/Graphemes_Sound_Letter_Patterns_Gold.docx",
"dest": "Graphemes_Sound_Letter_Patterns_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/Graphemes_Sound_Letter_Patterns.docx",
"dest": "Graphemes_Sound_Letter_Patterns.docx"
}
"func": [
"compare_docx_tables",
"compare_docx_tables"
],
"conj": "or",
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/936321ce-5236-426a-9a20-e0e3c5dc536f/Graphemes_Sound_Letter_Patterns_Gold.docx",
"dest": "Graphemes_Sound_Letter_Patterns_Gold.docx"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/936321ce-5236-426a-9a20-e0e3c5dc536f/Graphemes_Sound_Letter_Patterns_Gold_2.docx",
"dest": "Graphemes_Sound_Letter_Patterns_Gold_2.docx"
}
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/Graphemes_Sound_Letter_Patterns.docx",
"dest": "Graphemes_Sound_Letter_Patterns.docx"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/Graphemes_Sound_Letter_Patterns.docx",
"dest": "Graphemes_Sound_Letter_Patterns.docx"
}
]
},
"proxy": false
}

2
evaluation_examples/examples/os/4127319a-8b79-4410-b58a-7a151e15f3d7.json
View File

@@ -50,7 +50,7 @@
"type": "rule",
"rules": {
"include": [
"54\n"
"54"
],
"exclude": []
}

6
evaluation_examples/examples/vlc/bba3381f-b5eb-4439-bd9e-80c22218d5a7.json
View File

@@ -1,8 +1,8 @@
{
"id": "bba3381f-b5eb-4439-bd9e-80c22218d5a7",
"snapshot": "base_setup",
"instruction": "Can you start streaming the video from this link for me? https://www.youtube.com/watch?v=pgBsyTKAwLw",
"source": "https://www.quora.com/How-do-I-play-online-videos-using-the-VLC-media-player",
"instruction": "Can you start streaming the video from this link for me? https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8",
"source": "https://developer.apple.com/streaming/examples/ - Apple HLS test streams for developers",
"config": [
{
"type": "launch",
@@ -32,7 +32,7 @@
"type": "rule",
"rules": {
"type": "url",
"url": "https://www.youtube.com/watch?v=pgBsyTKAwLw"
"url": "https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8"
}
},
"result": {

2
evaluation_examples/examples/vs_code/276cc624-87ea-4f08-ab93-f770e3790175.json
View File

@@ -1,7 +1,7 @@
{
"id": "276cc624-87ea-4f08-ab93-f770e3790175",
"snapshot": "vscode",
"instruction": "Please help me set the current user's line length to 50 characters in VS Code.",
"instruction": "Please help me set the current user's line length for code wrapping to 50 characters in VS Code.",
"source": "https://www.quora.com/unanswered/How-do-you-set-the-line-length-in-Visual-Studio-Code",
"config": [
{

2
evaluation_examples/examples/vs_code/7c4cc09e-7a92-40dd-8338-b2286535c4ed.json
View File

@@ -1,7 +1,7 @@
{
"id": "7c4cc09e-7a92-40dd-8338-b2286535c4ed",
"snapshot": "vscode",
"instruction": "Please help me change the display language of VS Code to \"Arabic\".",
"instruction": "Please help me change the display language of VS Code to \"Arabic\" without using any extensions.",
"source": "",
"config": [
{