Our new X account is live! Follow @wizwand_team for updates

Phrase Grounding on Flickr30k (test)

87.5Accuracy

MM1.5-30B

Updated 4d ago

Evaluation Results

Method	Links
MM1.5-30B 2024.09		87.5	-	-	-	-
Ferret-V2-13B 2024.09		86.3	-	-	-	-
MM1.5-3B 2024.09		85.9	-	-	-	-
MM1.5-3B-MoE 2024.09		85.8	-	-	-	-
Ferret-V2-7B 2024.09		85.8	-	-	-	-
MM1.5-1B-MoE 2024.09		85.4	-	-	-	-
MM1.5-7B 2024.09		85.3	-	-	-	-
Ferret-13B 2024.09		84.8	-	-	-	-
BARE-L 2026.01		83.68	-	-	-	-
MM1.5-1B 2024.09		83	-	-	-	-
Ferret-7B 2024.09		82.2	-	-	-	-
InternVL2 2024.09		51.6	-	-	-	-
LLaVA-OneVision-7B 2024.09		50.1	-	-	-	-
Phi-3-Vision-4B 2024.09		27.12	-	-	-	-
MM1-1B 2024.09		0	-	-	-	-
MM1-3B 2024.09		0	-	-	-	-
MM1-7B 2024.09		0	-	-	-	-
MM1-30B 2024.09		0	-	-	-	-
HDC 2019.12		-	57.39	-	-	-
12-in-1 2019.12		-	64.61	-	-	-
DDPN 2022.05		-	-	73.5	-	-
UniTAB 2022.05		-	-	79.6	-	-
MDETR 2022.05		-	-	83.8	-	-
PEVL 2022.05		-	-	84.4	-	-
GLIP-T 2024.01		-	85.6	-	95.4	96.7
GLIP-T 2024.01		-	86	-	95.9	97.2
G-DINO-T(c) 2024.01		-	88.1	-	96.9	98.2
MM-G-T(b) 2024.01		-	86.2	-	95.7	97.4
MM-G-T(c1) 2024.01		-	87	-	96.2	97.7
MM-G-T(c2) 2024.01		-	87	-	96.2	97.7
MM-G-T(c3) 2024.01		-	87.2	-	96.2	97.7