{"id":"airoa-0","slug":"airoa-0","name":"AIRoA-0 (A-0)","orgId":"airoa","family":"airoa-0","releaseDate":null,"availability":"announced","openWeights":false,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://arxiv.org/abs/2611.03815","hfRepo":null,"modalities":["robotics"],"aliases":["AIRoA-0 (A-0)","airoa-0","airoa 0","a-0","A-0 robot","AIRoA A-0"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-04","announced":"2026-11-02","blurb":"AIRoA's robot foundation model pre-trained only on 16,151 hours of handheld human demonstrations recorded with the YUBI device, with no robot data.","api":"none","openWeights":"announced","facts":[{"label":"Pre-training data","value":"16,151 hours of YUBI handheld demonstrations; no robot data"},{"label":"Embodiments","value":"Bimanual Franka, TX-G2, OpenArm and UR, with two wrist cameras"},{"label":"Post-training","value":"Under 4 hours on one 8×H200 node (lab-stated)"},{"label":"Weights","value":"Lab says dataset, pre-trained weights and recipe are released; no weights repo located on Hugging Face as of Nov 4, 2026"}],"claims":["Lab claim: 78% average success across ten real-world tasks, versus 27% for the strongest of four other VLAs tested."],"sources":[{"kind":"paper","title":"AIRoA-0 (arXiv 2611.03815)","url":"https://arxiv.org/abs/2611.03815","date":"2026-11-02"},{"kind":"lab","title":"A-0 project page","url":"https://a-0.airoa.io"}],"firstBenchmark":null},"organization":{"id":"airoa","name":"AIRoA","slug":"airoa","country":null,"url":null,"color":"#11110F","mark":"A"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 2, 2026; no independent results yet.","lead":"As of Nov 22, 2026, AIRoA-0 (A-0) is pending benchmarks on isitsota: announced Nov 2, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}