inclusionAI releases Ling-3.1-flash-1019 with 560B parameters and 1M context window

·2026.10.27 20:12

Key point

The upgraded 560B-parameter model features a 1M-token context window and improved performance on reasoning and automation benchmarks.

inclusionAI introduces Ling-3.1-flash-1019, an upgraded version of Ling-3.1-flash with 560B total parameters, 25B active parameters per token, and a 1M-token context window.
Post-training optimizations raise the AA-Briefcase score from approximately 1400 to 1524 Elo and increase AutomationBench-AA performance from 62% to 68%.
The model scores 44 on the Artificial Analysis Intelligence Index v4.3.2, up from 41 for its predecessor, with gains in complex reasoning and multi-step task execution.
Scientific benchmark results improve, with CritPt rising from 18% to 26% and SciCode increasing from 54% to 57%.

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.