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

Multimodal Reasoning on SEED-Bench Image

74.2Score

Sphinx

Updated 1mo ago

Evaluation Results

Method	Links
Sphinx 2023.11		74.2	-	-	-	-	-	-	-	-	-	-
GPT4V 2023.11		74	-	-	-	-	-	-	-	-	-	-
Phantom-3.8B 2024.09		72.8	-	-	-	-	-	-	-	-	-	-
GPT4V 2023.11		72.5	-	-	-	-	-	-	-	-	-	-
Sphinx 2023.11		71.6	-	-	-	-	-	-	-	-	-	-
TroL-3.8B 2024.09		70.5	-	-	-	-	-	-	-	-	-	-
Sphinx 2023.11		70.3	-	-	-	-	-	-	-	-	-	-
LLaVA-1.5-13B 2023.11		69.7	-	-	-	-	-	-	-	-	-	-
CCoT 2023.11		69.7	59.3	76	74.4	71.8	64.3	54.5	79.2	58.8	74.2	-
MM1-MoE-3B×64 2024.09		69.4	-	-	-	-	-	-	-	-	-	-
GPT4V 2023.11		69.1	-	-	-	-	-	-	-	-	-	-
TroL-1.8B 2024.09		69	-	-	-	-	-	-	-	-	-	-
VidIL 2023.11		68.9	62.3	74.9	72.5	69.9	62.5	53.9	78	49.4	71.1	-
MM1-3B 2024.09		68.8	-	-	-	-	-	-	-	-	-	-
Phantom-1.8B 2024.09		68.6	-	-	-	-	-	-	-	-	-	-
LLaVA-1.5-13B 2023.11		68.2	-	-	-	-	-	-	-	-	-	-
LLaVA-1.5-13B 2023.11		66.7	-	-	-	-	-	-	-	-	-	-
DeepSeek-VL-1.3B 2024.09		66.7	-	-	-	-	-	-	-	-	-	-
ALLaVA-3B-Longer 2024.09		65.6	-	-	-	-	-	-	-	-	-	-
LLaVA-OneVision-0.5B 2024.09		65.5	-	-	-	-	-	-	-	-	-	-
ALLAVA-3B 2024.09		65.2	-	-	-	-	-	-	-	-	-	-
MiniCPM-2.4B 2024.09		62.9	-	-	-	-	-	-	-	-	-	-
Bunny-3B 2024.09		62.5	-	-	-	-	-	-	-	-	-	-
Phantom-0.5B 2024.09		60.6	-	-	-	-	-	-	-	-	-	-
QwenVL-Chat 2023.11		58.2	-	-	-	-	-	-	-	-	-	-
DDCoT 2023.11		58	47.3	63	59.8	64.1	44.6	41.4	67.1	57.7	51.6	-
mPlug-OWL2 2023.11		57.8	-	-	-	-	-	-	-	-	-	-
InstructBLIP-13B 2023.11		56.9	-	-	-	-	-	-	-	-	-	-
InstructBLIP-13B 2023.11		48.2	-	-	-	-	-	-	-	-	-	-
BLIP2 2023.11		46.4	-	-	-	-	-	-	-	-	-	-
InstructBLIP-13B 2023.11		37.6	-	-	-	-	-	-	-	-	-	-
MMCoT 2023.11		34.4	22.1	29.5	30.2	32.8	33.6	30.3	34.1	45.9	34	-
FineViT-VL 2026.03		-	-	-	-	-	-	-	-	-	-	77.44
Qwen3-VL 2026.03		-	-	-	-	-	-	-	-	-	-	74.78
Intern3.5-VL 2026.03		-	-	-	-	-	-	-	-	-	-	75.31
Aquila-VL 2026.03		-	-	-	-	-	-	-	-	-	-	73.9