{"id":"ling-3-1-flash-base","slug":"ling-3-1-flash-base","name":"Ling-3.1-flash-base","orgId":"inclusionai","family":"ling-3-1-flash-base","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/AntLingAGI/status/2115062200687878157","hfRepo":null,"modalities":["text"],"aliases":["Ling-3.1-flash-base","ling-3.1-flash-base","inclusionai/ling-3.1-flash-base","ling 3.1 flash base","ant ling 3.1 flash base"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-27","announced":"2026-10-27","blurb":"The base checkpoint of Ant Ling's Ling-3.1-flash: the pre-trained model before post-training, released as open weights under MIT for continued pre-training, domain adaptation and post-training research. A hybrid linear-attention mixture-of-experts model with 560B total and 25B active parameters. Not a chat model.","api":"none","openWeights":"yes","params":{"text":"560B total / 25B active","source":"Hugging Face model card (safetensors header: 572,120,680,768)"},"facts":[{"label":"Type","value":"Base checkpoint (no post-training); BF16 weights after Warmup-Stable and Merge (WSM) checkpoint merging; trained in FP8"},{"label":"Architecture","value":"Hybrid-linear MoE: 63 KDA + 9 Gated MLA layers (7:1), 4 dense layers, 512 routed experts with 8 routed + 1 shared active per token"},{"label":"Vocabulary","value":"157,184 tokens"},{"label":"Relation","value":"Base of Ling-3.1-flash and Ling-3.1-flash-1019 (tracked separately; their scores are not shared)"},{"label":"Weights","value":"Hugging Face inclusionAI/Ling-3.1-flash-base (BF16, 109 shards); announced Oct 27, 2026"},{"label":"License","value":"MIT"},{"label":"API","value":"None"}],"claims":["Lab claim: evaluated on 47 benchmarks across eight domains against DeepSeek-V4-Pro-Base and MiMo-V2.5-Pro-Base, e.g. MMLU-Pro 76.71 (5-shot) vs 75.28 and 71.26."],"sources":[{"kind":"lab","title":"Ant Ling on X: Ling-3.1-flash-1019 open source, plus Ling-3.1-flash-base","url":"https://x.com/AntLingAGI/status/2115062200687878157","date":"2026-10-27"},{"kind":"repo","title":"inclusionAI/Ling-3.1-flash-base on Hugging Face","url":"https://huggingface.co/inclusionAI/Ling-3.1-flash-base","date":"2026-10-27"}],"peer":{"slug":"ling-3-1-flash","label":"the post-trained model, Ling-3.1-flash"},"firstBenchmark":null},"organization":{"id":"inclusionai","name":"Ant Ling (InclusionAI, Ant Group)","slug":"inclusionai","country":null,"url":null,"color":"#11110F","mark":"A"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 27, 2026; no independent results yet.","lead":"As of Nov 3, 2026, Ling-3.1-flash-base is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}