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

Visual Question Answering on MMBench (dev)

60.1Overall Score

LLaVA-RLHF_13B×336

Updated 3d ago

Evaluation Results

Method	Links
LLaVA-RLHF_13B×336 2023.09		60.1	29.2	67.2	56.5	60.9	53.8	71.5	-
Kosmos-2 2023.09		59.2	46.7	55.7	43.5	64.3	49	72.5	-
Shikra_7B 2023.09		58.8	25.8	56.7	58.3	57.2	57.9	75.8	-
LLaVA-SFT+_13B×336 2023.09		57.5	25.8	65.7	54.8	57.9	51	68.5	-
IDEFICS_80B 2023.09		54.6	29	67.8	46.5	56	48	61.9	-
LLaVA-SFT+_7B 2023.09		52.1	28.3	63.2	37.4	53.2	35.9	66.8	-
Otter-I_9B 2023.09		51.4	32.5	56.7	53.9	46.8	38.6	65.4	-
LLaVA-RLHF_7B 2023.09		51.4	24.2	63.2	39.1	50.2	40	66.1	-
IDEFICS_9B 2023.09		48.2	20.8	54.2	33	47.8	36.6	67.1	-
LLaVA_13B×336 2023.09		47.5	23.3	59.7	31.3	41.4	38.6	65.8	-
InstructBLIP_13B 2023.09		44	19.1	54.2	34.8	47.8	24.8	56.4	-
LLaMA-Adapter_7B 2023.09		41.2	11.7	35.3	29.6	47.5	38.6	56.4	-
LLaVA_7B 2023.09		38.7	16.7	48.3	30.4	45.5	32.4	40.6	-
InstructBLIP_7B 2023.09		36	14.2	46.3	22.6	37	21.4	49	-
MiniGPT-4_7B 2023.09		24.3	7.5	31.3	4.3	30.3	9	35.6	-
OpenFlamingo_9B 2023.09		6.6	4.2	15.4	0.9	8.1	1.4	5	-
SAIL-VL 2025.01		-	-	-	-	-	-	-	72.4
Qwen2-VL 2025.01		-	-	-	-	-	-	-	68.8
InternVL2.5-MPO 2025.01		-	-	-	-	-	-	-	72.5
DeepSeekVL-2 2025.01		-	-	-	-	-	-	-	68.3
SAIL-VL 2025.01		-	-	-	-	-	-	-	79.5
Qwen2-VL 2025.01		-	-	-	-	-	-	-	79.5
InternVL2.5-MPO 2025.01		-	-	-	-	-	-	-	83.3
DeepSeekVL-2 2025.01		-	-	-	-	-	-	-	78.1