Ling 3.1 Flash
Fast hybrid-reasoning MoE (25B active / 560B) scoring 41 on the Intelligence Index.
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI (Ant Group), with 25B active parameters out of 560B total.
- Provider
- inclusionAI (Ant Group)
- Type
- Language model
- Released
- Oct 2, 2026
- Context window
- 262K tokens
- Max output
- 33K tokens
- Input
- text
- Output
- text
- Open weights
- No
Best for
- Reasoning
- Agents
- Real-time / low latency
- Long context
Strengths
- ~215 tok/s output
- Intelligence Index 41