SMH-Bench

What is SMH-Bench?

Benchmark for LLM agents in smart-home environments, with 1,100 tasks across 7 categories and 22 subcategories, built on the executable HomeEnv simulator…

Released

2026-06-01

Evaluates

Agents & Tool Use, General AI, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.01912

SMH-Bench paper

• Paper https://arxiv.org/abs/2606.01912

Which sources cite SMH-Bench?

• SMH-Bench

Related Agents & Tool Use, General AI, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveFly-Bench