Salvato in:
Dettagli Bibliografici
Autori principali: Sharrock, Callum, Petersson, Lukas, Petersson, Hanna, Backlund, Axel, Wennström, Axel, Nordström, Kristoffer, Aronsson, Elias
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.21860
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911230992580608
author Sharrock, Callum
Petersson, Lukas
Petersson, Hanna
Backlund, Axel
Wennström, Axel
Nordström, Kristoffer
Aronsson, Elias
author_facet Sharrock, Callum
Petersson, Lukas
Petersson, Hanna
Backlund, Axel
Wennström, Axel
Nordström, Kristoffer
Aronsson, Elias
contents We present Butter-Bench, a benchmark evaluating large language model (LLM) controlled robots for practical intelligence, defined as the ability to navigate the messiness of the physical world. Current state-of-the-art robotic systems use a hierarchical architecture with LLMs in charge of high-level reasoning, and a Vision Language Action (VLA) model for low-level control. Butter-Bench evaluates the LLM part in isolation from the VLA. Although LLMs have repeatedly surpassed humans in evaluations requiring analytical intelligence, we find humans still outperform LLMs on Butter-Bench. The best LLMs score 40% on Butter-Bench, while the mean human score is 95%. LLMs struggled the most with multi-step spatial planning and social understanding. We also evaluate LLMs that are fine-tuned for embodied reasoning and conclude that this training does not improve their score on Butter-Bench.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence
Sharrock, Callum
Petersson, Lukas
Petersson, Hanna
Backlund, Axel
Wennström, Axel
Nordström, Kristoffer
Aronsson, Elias
Robotics
Artificial Intelligence
We present Butter-Bench, a benchmark evaluating large language model (LLM) controlled robots for practical intelligence, defined as the ability to navigate the messiness of the physical world. Current state-of-the-art robotic systems use a hierarchical architecture with LLMs in charge of high-level reasoning, and a Vision Language Action (VLA) model for low-level control. Butter-Bench evaluates the LLM part in isolation from the VLA. Although LLMs have repeatedly surpassed humans in evaluations requiring analytical intelligence, we find humans still outperform LLMs on Butter-Bench. The best LLMs score 40% on Butter-Bench, while the mean human score is 95%. LLMs struggled the most with multi-step spatial planning and social understanding. We also evaluate LLMs that are fine-tuned for embodied reasoning and conclude that this training does not improve their score on Butter-Bench.
title Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2510.21860