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

Multi-modal Understanding on MMBench EN (Accuracy)

88.3Accuracy

InternVL2.5-78B

Updated 2d ago

Evaluation Results

Method	Links
InternVL2.5-78B 2024.12		88.3
InternVL2-40B 2024.12		86.8
InternVL2.5-38B 2024.12		86.5
Qwen2-VL-72B 2024.12		86.5
InternVL2-Llama3-76B 2024.12		86.5
LLaVA-OneVision-72B 2024.12		85.8
InternVL2.5-26B 2024.12		85.4
InternVL2.5-8B 2025.12		84.6
InternVL2.5-8B 2024.12		84.6
Qwen2.5-VL-7B 2025.12		83.5
InternVL2-26B 2024.12		83.4
GPT-4o-20240513 2024.12		83.4
Qwen2-VL-7B 2025.12		83
Qwen2-VL-7B 2024.12		83
Claude-3.5-Sonnet 2024.12		82.6
InternVL-Chat-V1.5 2024.12		82.2
CoT4DET-7B 2025.12		81.9
InternVL2-8B 2025.12		81.7
InternVL2-8B 2024.12		81.7
MiniCPM-V2.6 2024.12		81.5
InternVL2.5-4B 2024.12		81.1
GPT-4V 2024.12		81
LLaVA-OV-7B 2025.12		80.8
Cambrian-34B 2024.12		80.4
InternVL2-4B 2024.12		78.6
Phi-3.5-Vision-4B 2024.12		76
Qwen2-VL-2B 2024.12		74.9
InternVL2.5-2B 2024.12		74.7
Gemini-1.5-Pro 2024.12		73.9
InternVL2-2B 2024.12		73.2
InternVL2.5-1B 2024.12		70.7
InternVL2-1B 2024.12		65.4
Claude-3-Opus 2024.12		63.3
LLaVA-OneVision-0.5B 2024.12		61.6