Tether AI Research says BotPsy beats larger models in tool use
🎧 Listen to this story
Tether AI Research introduced BotPsy, a 0.8-billion-parameter model built on Qwen3.5-0.8B for function calling, agentic workflows and on-device deployment. The assistant uses tools for tasks including web research, travel, commerce, device control, files, calendars and messaging. The company says it is best suited to low- and medium-difficulty tasks and helps keep user data private.
Tether AI Research says BotPsy outperformed every tested model with up to 1.2 billion parameters across six tool-use and agentic benchmarks, while also beating Qwen3.5-2B-Think — 2.5 times larger — on five of them. However, the model can still make mistakes, performs worse in lower-resource languages and is not intended for high-stakes use. BotPsy is available in safetensors and GGUF formats.
Why it matters · editorial interpretation
A compact model designed for tool use could matter for on-device agents, especially where privacy and limited resources are important. However, the results come from Tether AI Research itself, and caveats about errors, lower-resource languages and high-stakes use limit the comparison’s scope.
Sources
ResearchAgents