Metraipolis › archive › dc_dcb1adbaa522

Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds — arXiv:2611.09017

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09017
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:12.574Z
SHA-256 of the archived text
3da2272cbb991764e64a0bdc409b13fcb32efaae50e97d6a1f801a2210a5a069
Stable URL of this page
https://metraipolis.com/documento/dc_dcb1adbaa522

How to cite

Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds — arXiv:2611.09017 — arXiv (en), https://arxiv.org/abs/2611.09017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcb1adbaa522 (Metraipolis archive dc_dcb1adbaa522, sha256 3da2272cbb991764e64a0bdc409b13fcb32efaae50e97d6a1f801a2210a5a069)
BibTeX
@misc{dcdcb1adbaa522,
  title = {Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds — arXiv:2611.09017},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09017},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcb1adbaa522; sha256 3da2272cbb991764e64a0bdc409b13fcb32efaae50e97d6a1f801a2210a5a069},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents combine visual understanding with program execution, offering a new route to automated 3D creation. By translating images and instructions into editable programs, they bring reconstruction, generation, and editing into a shared workflow. Yet existing benchmarks fragment evaluation across task scopes and protocols, leaving their capabilities across construction levels unclear. We propose Frontier3DBench, a unified benchmark of 145 tasks across 9 categories spanning object, scene, and interactive open-world creation, with joint evaluation of appearance, structure, and behavior. Experiments with 11 model-harness configurations reveal strengths that vary by level: GPT-6.1-sol leads the object and scene levels and achieves the highest overall score of 66.02/100, whereas GPT-6-astra leads interactive world construction. However, all configurations score lower on reference reconstruction than on text-driven generation in object and scene tasks. Producing plausible content thus remains easier than reproducing specified geometry, layouts, and visual details. Moreover, generated worlds average 83.08/100 on local mechanisms but only 20.82 on motion clearance and 30.26 on stateful workflows: individual mechanisms often function, whereas complete activities that require coordinated actions and persistent state remain difficult. These results identify reference fidelity and coordinated activity completion as central bottlenecks for coding agents in 3D creation.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.09017 — 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 2026-11-09T22:37:47.217Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).