--- format: "aidr-story-markdown/v1" id: "11f37b96aef03661cdbc40d0ced72bd524b1bc3661b9570ffe2132610005dab0" canonical_url: "https://aidr.today/11f37b96?lang=en" title: "Liquid AI and Artificial Analysis Launch Pipette With 10,000 Results as First Open Mobile AI Suite" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-08-24T18:52:08.000Z" category: "Research" topics: ["benchmark","open-source","inference","mobile-ai"] source_urls: ["https://huggingnews.com/ai/liquid-ai-and-artificial-analysis-launch-pipette-with-10000-results-as-f-d1363ee4","https://x.com/ArtificialAnlys/status/2091922042459406560","https://x.com/liquidai/status/2091906385693000074","https://x.com/ArtificialAnlys/status/2091922045278019948","https://x.com/ArtificialAnlys/status/2091922051074609499","https://x.com/ArtificialAnlys/status/2091922053238821319","https://x.com/ArtificialAnlys/status/2091922055331807506","https://x.com/ArtificialAnlys/status/2091922047643648233"] summary: "Nanbeige4.2-3B and LFM2.5-2.6B tied for the highest average intelligence score of 63 on the iPhone 17 Pro and Galaxy S26 Ultra. The evaluation, conducted by Artificial Analysis in partnership with Liquid AI, limited models to a 16K context window to mirror the memory constraints of handheld devices. LFM2.5-2.6B demonstrated higher efficiency by processing a 1,024 token prompt in 8.0 seconds using 2.3 GB of memory, while Nanbeige4.2-3B required 21.4 seconds and 4.0 GB. The partnership introduces Pipette, an open source benchmarking suite featuring a public dataset of 10,000 results across 35 model classes and four device types. Performance on the iPhone 17 Pro varied widely, with end to end generation times spanning 30x and peak memory usage spanning 19x among tested models. The tool includes macOS, Windows, iOS, and Android clients, allowing developers to measure quality, speed, and latency directly on target hardware." --- # Liquid AI and Artificial Analysis Launch Pipette With 10,000 Results as First Open Mobile AI Suite > [Open the canonical story]() **Published:** 2026-08-24T18:52:08.000Z **Category:** Research **Topics:** benchmark, open\-source, inference, mobile\-ai ## Summary Nanbeige4\.2\-3B and LFM2\.5\-2\.6B tied for the highest average intelligence score of 63 on the iPhone 17 Pro and Galaxy S26 Ultra\. The evaluation, conducted by Artificial Analysis in partnership with Liquid AI, limited models to a 16K context window to mirror the memory constraints of handheld devices\. LFM2\.5\-2\.6B demonstrated higher efficiency by processing a 1,024 token prompt in 8\.0 seconds using 2\.3 GB of memory, while Nanbeige4\.2\-3B required 21\.4 seconds and 4\.0 GB\. The partnership introduces Pipette, an open source benchmarking suite featuring a public dataset of 10,000 results across 35 model classes and four device types\. Performance on the iPhone 17 Pro varied widely, with end to end generation times spanning 30x and peak memory usage spanning 19x among tested models\. The tool includes macOS, Windows, iOS, and Android clients, allowing developers to measure quality, speed, and latency directly on target hardware\. ## Sources - [Story source]() - [Story source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]()