BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model

BotPsy achieves state-of-the-art tool-use and agentic performance for its size, outperforming every model of up to 1.2B parameters tested.

BotPsy scores 82.5 in telecom on τ²-bench, ahead of Qwen3.5-2B-Think (69.3).

In automated red-teaming, BotPsy produces unsafe responses 21% of the time, compared to 36% for its base model.

BotPsy's instruction following improves sharply, with IFEval rising from 59.7 to 90.8.