{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T14:05:46.489Z","data":{"recordId":"wsa_j9cd9uiecv53","score":0.86,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/LiquidAI/LFM3-VL-2B","publisher":"Liquid AI","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:20:34.693Z","detectedPublishedAt":"2026-10-19T19:51:46.000Z","rights":"original"},{"n":2,"url":"https://www.liquid.ai/blog/lfm3","publisher":"Liquid AI","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:20:11.464Z","detectedPublishedAt":"2026-10-27T00:00:00.000Z","rights":"original"},{"n":3,"url":"https://huggingface.co/blog/LiquidAI/lfm3","publisher":"Hugging Face","authority":"other","verification":"verified","lastRetrievedAt":"2026-10-28T00:19:24.915Z","detectedPublishedAt":"2026-10-27T17:16:52.000Z","rights":"original"}],"claims":[{"id":"2301b69b-fe72-4df4-b6ec-681b8435496c","kind":"availability","statement":"The LFM3 base and post-trained models are available today on Hugging Face, Liquid AI Playground, and Liquid AI API.","citations":[{"source":2,"supportProbability":0.55,"supports":false,"quote":{"text":"The base and post-trained models are open-weight and available today on Hugging Face , our Playground , and the Liquid AI API .","rights":"original"}}]},{"id":"de4d551f-fac0-476a-9f1a-94e538b3effa","kind":"capability","statement":"LFM3-VL-2B takes video as input.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":null},{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"Video understanding: for the first time, an LFM vision model takes video as input.","rights":"original"}},{"source":3,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"04c80145-d045-4a34-8b73-00fd171a4bc5","kind":"capability","statement":"The model reasons step by step before answering.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null},{"source":2,"supportProbability":0.99,"supports":true,"quote":{"text":"Thinking: the model reasons step by step before answering.","rights":"original"}},{"source":3,"supportProbability":0.81,"supports":true,"quote":null}]},{"id":"b800fe00-6328-40b2-94a3-351efc4728da","kind":"capability","statement":"The model can localize objects and reason about spatial relationships.","citations":[{"source":1,"supportProbability":0.93,"supports":true,"quote":null},{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"Spatial and embodied reasoning: the model’s ability to localize objects and reason about their spatial relationships provides a strong foundation for downstream robotics applications.","rights":"original"}},{"source":3,"supportProbability":0.8,"supports":true,"quote":null}]},{"id":"70eefcef-606a-4f6e-8871-108e3f774f7d","kind":"recommendation-relevant","statement":"The source reports that LFM3-VL-2B scored significantly ahead of similarly sized models across 62 vision benchmarks.","citations":[{"source":2,"supportProbability":0.98,"supports":true,"quote":{"text":"Across 62 vision benchmarks, LFM3-VL-2B scores significantly ahead of all models of similar size by at least 7.4 points, and despite its size, it matches the performance of Gemma 4 12B, a model more than 6 times larger, surpasses Gemini 3.5 Flash Lite and is within 2 points of…","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}