Share your thoughts, 1 month free Claude Pro on usSee more

Visual Question Answering on VQAv2, VizWiz, GQA, TextVQA, and MME

64.9GQA Accuracy

CogVLM-7B

Updated 9d ago

Evaluation Results

Method	Links
CogVLM-7B 2025.10		64.9	82.3	-	78.2	71.8	-
Qwen2.5-VL-7B 2025.10		63.9	82.8	61.7	73.9	83.9	73.2
LLaVA-7B† 2025.10		63.8	81.4	50.6	64.6	77.5	67.6
Imp-3B 2025.10		63.5	81.2	54.1	59.8	72.3	66.2
MoE-LLaVA-3B 2025.10		62.6	79.9	43.7	57	71.6	63
Bunny-3B 2025.10		62.5	79.8	43.8	56.7	74.4	63.4
LLaVA-7B† 2025.10		62.3	79.8	53.1	60.1	68.6	64.8
LLaVA-KD-2B 2025.10		62.3	78.8	44.8	53.4	68.9	61.6
CompoDistill-2B 2025.10		62.2	78.8	42.5	56.4	70.1	61.9
LLaVA-4B† (Teacher) 2025.10		62.1	79.1	48	56.7	67.2	62.6
Imp-2B 2025.10		61.9	79.2	39.2	54.5	65.2	60
MoE-LLaVA-2B 2025.10		61.5	76.2	32.6	48	64.6	56.6
Deepseek-VL-7B 2025.10		61.3	-	49.9	64.7	73.4	-
MobileVLM-3B 2025.10		61.1	-	-	57.5	72	-
Qwen2.5-VL-3B 2025.10		60.9	80.4	54.1	68.5	72.8	67.3
MiniGemini-2B 2025.10		60.7	-	41.5	56.2	67	-
Bunny-2B 2025.10		59.6	76.6	34.2	53.2	65	57.7
Deepseek-VL-1.3B 2025.10		59.3	-	36.8	58.4	65.3	-
MobileVLM-1.7B 2025.10		59.3	-	-	52.1	65.1	-
LLaVA-MoD-2B† 2025.10		58.8	76.3	43	52.7	63.4	58.9
LLaVADI-2B† 2025.10		58.7	75.8	35.2	49.4	63.8	56.6
LLaVA-2B (SFT model) 2025.10		57.9	73.6	31.2	50.6	61.2	54.9
MiniCPM-V 2025.10		52.1	-	60.2	73.2	70.5	-