Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Grounding research benchmarks · SOTA2 Research

Grounding

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

51.8Average Grounding Accuracy

82

Jun 23, 2026

GUIrilla-See (7B)

94.73Grounding Accuracy

50

Jun 23, 2026

ScreenSpot v2 (test)

UI-Venus-Ground-72B

95.3Overall Accuracy

29

Apr 16, 2026

90.06Score

28

Mar 4, 2026

92.8Accuracy

23

Jul 8, 2026

64.7Overall Score

22

Apr 14, 2026

UI-Venus-1.5-30B-A3B

76.4Accuracy

22

Jun 23, 2026

MeCo (ETChat 7B)

62.5TVG F1

20

Feb 26, 2026

refCOCO (testB)

91.5Accuracy

18

May 29, 2026

UI-Venus-1.5-30B-A3B

54.7Accuracy

18

Feb 26, 2026

91.3Accuracy

18

Feb 26, 2026

UI-Venus-1.5-30B-A3B

75Accuracy

18

Feb 26, 2026

OSWorld-G-Refine (test)

UI-Venus-1.5-30B-A3B

76.4Overall Success Rate

17

Jul 1, 2026

UHR-Micro (test)

29.79GD Score

16

May 13, 2026

36.46LasHeR

15

Feb 26, 2026

86.77Score

14

Mar 4, 2026

ScreenSpot-Pro macOS

GUIrilla-See (7B)

41.39Grounding Accuracy

13

Mar 25, 2026

Breast Ultrasound same-center (val)

Echo-α-Grounding

52.96F1 Score @ IoU=0.25

12

May 1, 2026

Renal Ultrasound cross-center (test)

Echo-α-Grounding

69F1 Score @ IoU=0.25

12

May 1, 2026

FigTalk-Gold Hard (reference set)

74.2Macro F1

9

Jun 12, 2026

FigTalk-Gold Medium (reference set)

70.4Macro F1

9

Jun 12, 2026

FigTalk-Gold Easy (reference set)

77.8Macro F1

9

Jun 12, 2026

FigTalk-Gold All (reference set)

74.3Macro F1

9

Jun 12, 2026

T-SROIE dense text for robustness (test)

9.1mIOU

8

Apr 6, 2026

T-IC13 adapted (test)

44.5mIoU

8

Apr 6, 2026

Page 1 of 2

PreviousNext

Popular datasets

ScreenSpot RefCOCO OSWorld Grounding RefCOCOg

Follow for updates

Join SOTA2 Contact