SOTA Grounding benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
ScreenSpot Pro	UI-AGILE-7B + Decomposed Grounding	Average Grounding Accuracy48.7	33	9d ago
ScreenSpot V2	MAI-UI-32B	Accuracy96.5	32	9d ago
ScreenSpot v2 (test)	UI-Venus-Ground-72B	Overall Accuracy95.3	29	3d ago
RefCOCO	TIES Merging	Score90.06	28	1mo ago
OSWorld	MGA w/ GPT-5	Overall Score64.7	22	4d ago
E.T. Bench	MeCo (ETChat 7B)	TVG F162.5	20	1mo ago
OSworld G-R	UI-Venus-1.5-30B-A3B	Accuracy76.4	19	1mo ago
UI-Vision	UI-Venus-1.5-30B-A3B	Accuracy54.7	18	1mo ago
MMbench	MAI-UI-32B	Accuracy91.3	18	1mo ago
VenusBench GD	UI-Venus-1.5-30B-A3B	Accuracy75	18	1mo ago
RGBX-Grounding	RGBX-R1	LasHeR36.46	15	1mo ago
RefCOCOg	TIES w/ DARE	Score86.77	14	1mo ago
ScreenSpot-Pro macOS	GUIrilla-See (7B)	Grounding Accuracy41.39	13	24d ago
T-SROIE dense text for robustness (test)	DocShield	mIOU9.1	8	13d ago
T-IC13 adapted (test)	DocShield	mIoU44.5	8	13d ago
RealText proposed (test)	DocShield	mIOU32.4	8	13d ago
Custom Dataset	GROUNDIT	mIoU25	8	1mo ago
HRS-Spatial	GROUNDIT	mIoU0.372	8	1mo ago
MS-COCO 2014	GROUNDIT	mIoU43.2	8	1mo ago
Flickr30k Entities (test)	Up-Down w/ DPA	F1 (All)5.45	7	1mo ago
VRSBench (val)	GeoChat	Accuracy @ IoU 0.549.8	5	1mo ago
AMEX (test)	CoME	Grounding Score79.19	4	1mo ago
ChestXDet10	CARZero	Mean Localization Score54.3	4	1mo ago
Grounding Adv. Messy	LLM (Qwen3 8B)	Adjusted Accuracy91	3	1mo ago
Grounding (Messy)	LLM (Qwen3 8B)	Adjusted Accuracy100	3	1mo ago

Showing 25 of 27 rows