The Ling-3.1-flash-1019 model weights have been released, featuring a 1 million token context window and a total of 560 billion parameters with 25 billion active. This update improves upon the previous version, with the AA Intelligence Index score rising from 41 to 44 and AutomationBench-AA increasing from 62% to 68%. Additionally, the base model, Ling-3.1-flash-base, has been made available for further training, allowing users to fine-tune their own models. AI
IMPACT Provides a new model with a large context window for researchers and developers to utilize and fine-tune.
RANK_REASON Release of model weights for a specific AI model.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →