Tether's Tiny AI Agent Beats Models 2.5 Times Its Size at Controlling Your Phone
Tether's new 800-million-parameter BotPsy AI agent outperformed models 2.5 times larger on five of six tool-use benchmarks in company testing.
Unlike traditional chatbots that simply respond to questions, BotPsy is agentic, meaning it's designed to take action. It can identify which tools an application needs, execute commands in the right order, and adjust when something goes wrong.
For example, Tether described a benchmark scenario where an AI assistant needed to send a message but encountered two problems: Wi-Fi was disabled and the inbox was full. BotPsy turned on Wi-Fi, cleared enough storage, and completed the task, while the underlying model repeatedly attempted the same failed operation.
Performance Benchmarks
BotPsy is built on Alibaba's Qwen3.5-0.8B architecture, a relatively small language model that Tether trained further to specialize in interacting with software tools. Its 800 million parameters represent the numerical values the model learned during training.
According to Tether's technical documentation, BotPsy scored 44.0% on BFCL v4, a benchmark that evaluates an AI system's ability to select and execute software functions across different tasks and conversations. The underlying Qwen3.5-0.8B model scored 23.4%, while the considerably larger Qwen3.5-2B reached 37.7%.
BotPsy also scored 58.7% on ACEBench, which evaluates the accuracy of function calls. Its base model managed 30.1%, while the 2-billion-parameter competitor scored 55.4%. The company tested five models across six tool-use evaluations, with BotPsy posting the highest results on five.
QVAC Ecosystem Expansion
BotPsy is the latest addition to QVAC, Tether's effort to build an AI ecosystem that runs on devices controlled by users rather than relying entirely on centralized cloud infrastructure. The company first introduced QVAC in May 2025, positioning the project as an alternative to AI services operated by technology giants.
Tether expanded that initiative in October 2025 with a 41-billion-token dataset for training science and engineering models, alongside QVAC Workbench, an application that lets users run AI models locally. Earlier this year, Tether released its SDK, providing developers with tools to build offline AI applications across mobile and desktop operating systems.
The company also developed QVAC MedPsy, a medical AI system designed to run on consumer hardware. Its 1.7-billion-parameter version outperformed Google's much larger MedGemma-27B on HealthBench Hard, a test of realistic clinical conversations evaluated using physician-developed criteria.
Availability and Future Plans
BotPsy is currently available as an open-weight model under the Apache 2.0 license, meaning developers can download, modify, and integrate it into their own applications. Tether has also released compressed versions intended to reduce memory requirements for local deployment.
The company has not announced a release date for a finished consumer assistant powered by BotPsy. Its published model card also says the training code and training data are not included in the release.
Related
