Search: document understanding
🇨🇳 ChinaQwen2.5-VL
Vision-language model for images, documents and long videosMultimodal · Open weights · 2025
🇰🇷 South KoreaEXAONE 4.5
Open-weight vision-language model from LG AI ResearchMultimodal · Open weights
🇺🇸 United StatesNemotron 3.5 Super VL
NVIDIA's open-weight vision-language model with 120B parameters and 1M-token contextMultimodal · Conditional licence · 2026