Ant Ling introduces Ling-3.2-flash, a 560B multimodal model that it says beats Opus 5 on three benchmarks

Ant Ling announced Ling-3.2-flash, which it calls a native multimodal model with 560B total and 25B active parameters. It says the model is stronger at complex visual understanding, long-horizon multimodal agents, 3D understanding and interaction, and medical intelligence.

Ant Ling's own release evaluations, which are not independently confirmed, say it outscores Opus 5 (max) on three benchmarks:

• OmniDocBench1.5: 92.21 vs 90.56
• ZEROBench (Sub): 43.71 vs 39.52
• Vision2Web: 85.86 vs 80.20

Its demos show the model coordinating specialist agents to turn financial data into a report, a six-slide deck and a highlights video; building responsive frontends and operating Blender; recreating game assets in 3D from a single 2D reference image; turning research PDFs into working code; and estimating calories and nutrients from meal photos. Ant Ling says users can try the model on Computrix.