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

Large Vision-Language Modeling on Tiny LVLM (test)

64.2VR

Bard

Updated 2d ago

Evaluation Results

Method	Links
Bard 2023.12		64.2	319.6	57	68.1	59.6	70.7
Bard 2023.09		64.2	319.6	57	68.1	59.6	70.7
Qwen-VL-Chat 2023.12		62.4	316.8	54.5	55.1	54.8	90
Qwen-VL-Chat 2023.09		62.4	316.8	54.5	55.1	54.8	90
InternVL-Chat 2023.12		56.4	327.6	52.3	68	62	89
InternLM-XComposer 2023.12		55.8	322.5	53.8	64.1	61.8	87
InternLM-XComposer 2023.09		55.8	322.5	53.8	64.1	61.8	87
LLaVA-1.5 2023.12		55.6	307.2	49	57	57.2	88.3
LLaVA-1.5 2023.09		55.6	307.2	49	57	57.2	88.3
Lynx 2023.12		52.2	279.2	65.8	17.6	57.4	86.3
Lynx 2023.09		52.2	279.2	65.8	17.6	57.4	86.3
InstructBLIP 2023.12		46.7	300.6	48	61.7	59.2	85
InstructBLIP 2023.09		46.7	300.6	48	61.7	59.2	85
BLIP-2 2023.12		44.9	284.7	49	64.1	44	82.7
BLIP2 2023.09		44.9	284.7	49	64.1	44	82.7
LLaMA-Adapter-V2 2023.12		43.5	229.2	46.8	22.3	56	60.7
LLaMA-A-V2 2023.09		43.5	229.2	46.8	22.3	56	60.7
LLaVA 2023.12		41.6	197	38.3	18.7	49.4	49
Otter 2023.12		41.6	216.4	37	15.1	52.4	74
LLaVA 2023.09		41.6	197	38.3	18.7	49.4	49
Otter 2023.09		41.6	216.4	37	15.1	52.4	74
MiniGPT-4 2023.12		37.6	192.6	37.8	17.6	49	50.7
MiniGPT-4 2023.09		37.6	192.6	37.8	17.6	49	50.7
VisualGLM 2023.12		37.3	211.9	36.3	46.9	37.6	54
VisualGLM 2023.09		37.3	211.9	36.3	46.9	37.6	54