Multimodal Retrieval

Benchmarks

Dataset Name	SOTA Method	Metric
MMEB	UniME-V2	Classification Score788.1	50	3d ago
Multi30k (test)	CCLM	Recall (EN)97.8	35	3d ago
MT-FIQ	V-Retrver-7B	Recall@568.3	15	3d ago
WikiVideo (test)	RankVideo	Alpha-nDCG62.8	10	3d ago
MULTIMODALQA Doc (test)	VISRAG	Total Time (ms)371	10	3d ago
WholeHouse-MM (test)	Affordance RAG	Target Object Recall@532.8	9	3d ago
RAVENEA (test)	Ravenea-CLIP	MRR82.17	7	3d ago
VisD	V-Retrver-7B	R@175.1	7	3d ago
GeneCIS	V-Retrver-7B	Recall@130.7	7	3d ago
EDIS-2	GME-2B	Recall@570.32	6	3d ago
OVEN-8	GME-2B	R@575.98	6	3d ago
OVEN-6	GME-2B	R@558.17	6	3d ago
InfoSeek-8	Reasoning-Augmented Representations	Recall@552.38	6	3d ago
InfoSeek 6	Reasoning-Augmented Representations	R@542.08	6	3d ago
WebQA 2	GME-2B	R@583.15	6	3d ago
WebQA 1	GME-2B	Recall@595.19	6	3d ago
Nights-4	Reasoning-Augmented Representations	R@531.56	6	3d ago
VisNews 3	CLIP	R@541.3	6	3d ago
VisNews 0	CLIP	R@543.3	6	3d ago
MSCOCO 3	Reasoning-Augmented Representations	Recall@590.02	6	3d ago
MSCOCO 0	Reasoning-Augmented Representations	Recall@580.2	6	3d ago
OI-Pos	FuseLIP	Clean Accuracy69.2	5	3d ago
OI-Crop	FuseLIP	Clean Accuracy71.8	5	3d ago
MMCOQA Doc (test)	VISRAG	Total Time (ms)362	5	3d ago
MSCOCO 2 modal	CLIP (LT)	Gap0.47	4	3d ago

Showing 25 of 26 rows