Ant Group's Ling team has open-sourced Ling-3.1-flash-1019, which scored 44 on the Artificial Analysis Intelligence Index v4.3.2, up from 41 for the previous Ling-3.1-flash version. The team also released the base model Ling-3.1-flash-base, allowing developers to continue training on it. The new release features further post-training optimizations for reasoning and agentic workflows. Benchmark improvements include AA-Briefcase rising from approximately 1,400 to 1,524 Elo, AutomationBench-AA increasing from 62% to 68%, CritPt jumping from 18% to 26%, and SciCode improving from 54% to 57%. Both models are now available on Hugging Face and ModelScope.