Holo2-4B / .eval_results /screenspot_pro.yaml
marc-thibault-h's picture
Add ScreenSpot-Pro evaluation result (Holo2-4B) (#2)
44b1259
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: overall
value: 57.2
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: android_studio_macos
value: 62.5
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: autocad_windows
value: 14.7
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: blender_windows
value: 43.7
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: davinci_macos
value: 54.5
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: eviews_windows
value: 92.0
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: excel_macos
value: 73.4
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: fruitloops_windows
value: 43.9
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: illustrator_windows
value: 41.9
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: inventor_windows
value: 34.3
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: linux_common_linux
value: 66.0
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: macos_common_macos
value: 70.8
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: matlab_macos
value: 69.9
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: origin_windows
value: 38.7
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: photoshop_windows
value: 47.1
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: powerpoint_windows
value: 76.8
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: premiere_windows
value: 40.4
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: pycharm_macos
value: 59.0
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: quartus_windows
value: 42.2
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: solidworks_windows
value: 28.6
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: stata_windows
value: 42.9
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: unreal_engine_windows
value: 71.4
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: vivado_windows
value: 70.0
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: vmware_macos
value: 85.4
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: vscode_macos
value: 52.7
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: windows_common_windows
value: 50.6
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: word_macos
value: 83.3
source:
url: https://gui-agent.github.io/grounding-leaderboard/
name: ScreenSpot-Pro Leaderboard
user: merve