Tether 800M AI Agent Outperforms Models 2.5x Its Size on Phone Tasks

Tether's Tiny AI Agent Beats Models 2.5 Times Its Size at Controlling Your Phone

BotPsy packs 800 million parameters into an AI assistant designed to manage everyday tasks locally, outperforming larger rivals as Tether expands its push into decentralized artificial intelligence.

Tether 800M AI Agent Outperforms Models 2.5x Its Size on Phone Tasks

TL;DR Tether AI Research released BotPsy-0.8B, an 800-million-parameter open-weight model designed for local AI agents that can execute multi-step phone and tool tasks. In Tether’s testing, BotPsy beat Qwen3.5-2B-Think despite being 2.5 times smaller and roughly doubled its base model’s scores across four core agentic benchmarks. The model also led tested systems on BFCL hallucination ...

Tether’s 800M AI Agent Outperforms Models 2.5 Times Its Size in Six Tool-Use Tests

Key Takeaways: Tether’s QVAC BotPsy-0.8B beat models with up to 2.5 times more parameters in six agentic tests. The tool-use score of the 800M-parameter model almost doubled the scores of

Tether's BotPsy AI model outperforms larger models in benchmarks

BotPsy's success highlights a shift towards efficient, smaller AI models, potentially lowering hardware requirements for on-device assistants.