# ModelScope introduces Ling-3.1-flash-1019, a 560B open-weight MoE model

> Original title: Post-training gains for agents and scientific reasoning: Ling-3.1-flash-1019 is a 560B open-weight MoE with 25B active parameters per tok...

- Source: ModelScope
- Published: 2026-10-28T01:52:35.000Z
- Bad Influence: https://badinfluence.news/items/zxzdqckekbxfrnrxtdfkpes16
- Original: https://x.com/ModelScope2022/status/2115260406763524368

## Summary

ModelScope announces Ling-3.1-flash-1019, a 560B open-weight mixture-of-experts model with 25B active parameters per token and support for up to 1M context. It reports gains over its predecessor Ling-3.1-flash: AA-Briefcase Elo rises from about 1400 to 1524, AutomationBench-AA from 62% to 68%, and Artificial Analysis Intelligence Index v4.3.2 from 41 to 44. The model is released under the MIT License, and reaching full 1M context requires an appropriate long-context serving configuration.

## Post

Post-training gains for agents and scientific reasoning: Ling-3.1-flash-1019 is a 560B open-weight MoE with 25B active parameters per token and support for up to 1M context.
🤖 https://modelscope.ai/models/inclusionAI/Ling-3.1-flash-1019 

🛠️ Stronger real-world agents: AA-Briefcase improves from approximately 1400 to 1524 Elo, while AutomationBench-AA rises from 62% to 68% versus Ling-3.1-flash.
🧠 Broader reasoning gains: Scores 44 on the Artificial Analysis Intelligence Index v4.3.2, up from 41 for its predecessor.
🔬 Better scientific performance: CritPt increases from 18% to 26%, and SciCode from 54% to 57%.
📐 Hybrid long-context design: Combines 63 KDA layers with 9 Gated MLA layers. Reaching the full 1M context requires the appropriate long-context serving configuration.
📜 MIT License.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVrqIWcXEAAH_WE.jpg&mode=thumb&exp=1793404800&sig=4ccf1079c93fadc4)