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

Merge branch 'main' into fix_chrome

Browse Source
This commit is contained in:
yuanmengqi
2025-07-13 10:16:08 +00:00
parent a16b54c175
commit 572a94b6df
15 changed files with 228 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
evaluation_examples/examples/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f.json
View File

@@ -144,17 +144,46 @@
"os"
],
"evaluator": {
"func": "compare_epub",
"result": {
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass Through.epub"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
}
"func": [
"compare_epub",
"compare_epub",
"compare_epub"
],
"conj": "or",
"result": [
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass Through.epub"
},
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass_Through.epub"
},
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/pass_through.epub"
}
],
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
}
]
},
"proxy": true
}