Metraipolis › archive › dc_3bf35b6619de

PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models — arXiv:2608.14741

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14741
License (as archived)
CC0-1.0
Archived
2026-10-18T17:52:35.052Z
SHA-256 of the archived text
834970006ca6700effd2578269bcb41833407410adbb5307544fafc91ba8f39c
Stable URL of this page
https://metraipolis.com/documento/dc_3bf35b6619de

How to cite

PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models — arXiv:2608.14741 — arXiv (en), https://arxiv.org/abs/2608.14741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3bf35b6619de (Metraipolis archive dc_3bf35b6619de, sha256 834970006ca6700effd2578269bcb41833407410adbb5307544fafc91ba8f39c)
BibTeX
@misc{dc3bf35b6619de,
  title = {PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models — arXiv:2608.14741},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14741},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3bf35b6619de; sha256 834970006ca6700effd2578269bcb41833407410adbb5307544fafc91ba8f39c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning. In each problem, a model must identify which of four options shows a pair of polycube components that can be combined to form a target solid. The benchmark contains 120 problems across four geometry families, and each problem has three different presentation formats using either a single image or multiple images. The random guessing baseline is 25%. Across the three presentations (360 presented problems per model), GPT-5.6 Sol with max effort attains 50.0% accuracy (95% problem-cluster CI 43.3-56.7%) at a mean cost of \$0.951 per presented problem, Claude Fable 5 with max effort attains 39.4% (33.1-46.1%) at \$0.701, and Gemini 3.1 Pro Preview with thinking level high attains 27.5% (22.8-32.5%), near the 25% random guessing baseline, at \$0.350. The observed accuracy spread across geometry families is larger than across presentation formats. We present a problem development and evaluation protocol, cost and token accounting, and release the 120 problems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14741 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.953Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).