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

Multimodal Reasoning on MMBench (dev)

87.6Accuracy

GPT-4o

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4o 2024.05		87.6
GPT-4o 2024.05		86.2
Gemini-Pro-1.5 2024.05		79.6
InternLM-XComposer2-VL 2024.05		79.5
Qwen-VL-Max 2024.05		78.1
LLaVA-FA-7B 2026.01		74.5
Deepseek-VL-7B 2026.01		74.1
Imp-3B 2026.01		72.9
Gemini-Pro-1.5 2024.05		71
LLaVA-FA-3B 2026.01		70.5
LLaVA-NeXT 2026.01		70.4
LLaVA-v1.5-13B 2024.05		69.2
VILA-7B 2026.01		68.9
Bunny-3B 2026.01		68.6
MiniCPM-V-2 2026.01		68.5
LLaVA-FA-2B 2026.01		66.7
Qwen-VL-Plus 2024.05		66.2
MoE-LLaVA-3B 2026.01		65.2
DeepSeek-VL-1.3B 2026.01		64.6
LLaVA-1.5 2023.12		64.3
LLaVA-1.5-7B 2026.01		64.3
MiniCPM-V 2026.01		64
Imp-2B 2026.01		63.8
CogVLM 2026.01		63.7
VILA-3B 2026.01		63.4
MobileVLMv2 2026.01		63.2
Qwen-VL-Chat 2026.01		60.6
Mini-Gemini-2B 2026.01		59.8
MoE-LLaVA-2B 2026.01		59.7
MobileVLM 3B 2023.12		59.6
MobileVLM 2026.01		59.6
Bunny-2B 2026.01		59.1
Shikra 2023.12		58.8
LLaVA-FA-1B 2026.01		58.3
MobileVLM 3B w/ LORA 2023.12		57
SPHINX-Tiny 2026.01		56.6
IDEFICS-80B 2023.12		54.5
MobileVLM 1.7B 2023.12		53.2
MobileVLM 1.7B w/ LORA 2023.12		50.4
mPLUG-Owl 2023.12		49.4
IDEFICS-9B 2023.12		48.2
Qwen-VL 2023.12		38.2
InstructBLIP 2023.12		36
MiniGPT-4 2024.05		24.3
MiniGPT-4 2023.12		23
MiniGPT-v2 2023.12		12.2
Openflamingo 2023.12		4.6