Ant's Ling-3.2-flash: 560B/25B active multimodal model beats Opus 5 on vision benchmarks
Med1_Ai · x · 2026-11-12
Ant Ling released Ling-3.2-flash, a natively multimodal MoE model with 560B total / 25B active parameters, targeting complex visual understanding, long-horizon multimodal agents, 3D understanding & interaction, and medical intelligence.
In release evaluations it outscores Claude Opus 5 (max) on three benchmarks: OmniDocBench1.5 (92.21 vs 90.56), ZEROBench(Sub) (43.71 vs 39.52), and Vision2Web (85.86 vs 80.20). Demos show it turning designs into frontends, driving Blender, and converting engineering drawings into 3D models — not just interpreting images but acting on them.
More from Models
- Judgement small models become essential: four companies ship within eight weeks — FinanceYF5 · 2026-11-12
- Addy Osmani's guide to picking a Claude model: start with Opus at medium effort — bibryam · 2026-11-12
- Google expands academic research access program with free Gemini 4 Carbon for scientists — pushmeet · 2026-11-12
- SoftBank found 15,000 vulns with OpenAI's tool, then GPT-6 Astra surfaced 35,000 more — IgorCarron · 2026-11-12
- Kakao ships on-device small model Raon-1 nano, proven in PUBG and PlayinZOI — Kangwook_Lee · 2026-11-12
- Meta releases MetaEncoder: one bi-encoder for retrieval and decision-making via natural language — pmttyji · 2026-11-12