Ant Group open-sources Ling-3.1-flash-1019，AA Intelligence Index rises to 44
BIBIBI
AT A GLANCE
Ant Group open-sourced Ling-3.1-flash-1019 and announced improvements in multiple evaluation scores.
Article
Ant Group open-sourced Ling-3.1-flash-1019，AA intelligence score rose to 44
PANews October 27 According to a message, the Ant Group Ling team announced on the official Ant Ling X account that it had open-sourced Ling-3.1-flash-1019. The model scored v4.3.2 on the Artificial Analysis Intelligence Index 44，Ling-3.1-flash with a score of 41. The team also open-sourced the base model Ling-3.1-flash-base, for developers to continue training. The new version underwent further post-training focused on reasoning and agent workflows.AA-Briefcase rose from approximately 1400 to 1524 Elo，AutomationBench-AA from 62%rose to 68%rose from 18%to 26%，Sc...
Key points
01
Ant Group's Ling team announced the open-sourcing of Ling-3.1-flash-1019。
02
Ling-3.1-flash-1019 and scored v4.3.2 on the Artificial Analysis Intelligence Index 44，Ling-3.1-flash score 41。
03
The team also open-sourced the base model Ling-3.1-flash-base for developers to continue training.
04
AA-Briefcase increased from approximately 1400 to 1524 Elo，AutomationBench-AA from 62% to 68%; CritPt increased from 18% to 26%。
AI-assisted interpretation
The following is analysis, separate from reported facts. Verify important claims independently.
This is a model released and made available for use by Ant Group’s Ling team. The base model allows developers to continue training it; reports indicate that the new version scored higher than the previous version on multiple evaluation benchmarks.
Why it matters to readers
Open-source models and base models may provide developers with further subjects for use and training, but actual adoption has not been established in the evidence.
You can understand it as follows: the Ant team released a model that external users can use and continue training, and described its performance using scores from multiple tests.
Risks and unknowns
The original text is a truncated summary, and complete details of the subsequent evaluations are not provided.
The evidence does not provide an official announcement, model weights, or a specific open-source link; the scope of its open-source availability still needs verification.
The evidence does not state actual developer adoption or the results of third-party retesting.
Related Developments
Loading event timeline…
Related concepts
Open-Source Models
This term is not in the glossary yet. Browse related concepts in the glossary.
