Ant Ling releases the native multimodal model Ling-3.2-flash, with 560B total parameters and 25B activated
Ant Ling releases the native multimodal model Ling-3.2-flash, with 560B total parameters and 25B activated parameters, focusing on complex visual understanding, long-horizon multimodal agents, 3D understanding and interaction, and medical intelligence. In the official release evaluations, the model scored 92.21 on OmniDocBench1.5, 43.71 on ZEROBench(Sub), and 85.86 on Vision2Web, all higher than Opus 5 (max)'s 90.56, 39.52, and 80.20.
Why read this
SelectedAI score 71
The official comparison figures against Opus 5 on three benchmarks can be used to assess the capability positioning of this multimodal model.
Topics
Body
Introducing Ling-3.2-flash, Ant Ling's native multimodal model: 560B total / 25B active parameters. Stronger complex visual understanding, long-horizon multimodal agents, 3D understanding & interaction, and medical intelligence. Outscores Opus 5 (max) in release evaluations: - OmniDocBench1.5: 92.21 vs 90.56 - ZEROBench(Sub): 43.71 vs 39.52 - Vision2Web: 85.86 vs 80.20