基准测试博士级编码在3D几何计算机视觉中的表现
Benchmarking PhD-Level Coding in 3D Geometric Computer Vision
GeoCodeBench 提供了从论文官方仓库中筛选核心 3D 几何组件并自动生成边界单元测试的流程，可直接用于评估或训练模型实现几何变换、算法逻辑等 3D 视觉代码的能力，其上下文消融结果（截断至方法部分优于全文）也为科学长文档理解提供了可复用的实验设计。
原文依据 we introduce GeoCodeBench, a PhD-level benchmark that evaluates coding for 3D vision
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论AI辅助编码已迅速重塑软件实践与研究流程，然而当今模型仍难以针对复杂3D几何视觉生成正确代码。若模型能可靠地编写此类代码，本社区的研究将发生实质性变化。为衡量朝该目标取得的进展，我们提出GeoCodeBench，一个评估3D视觉编码的博士级基准。每个问题均为从近期会议代表性论文中精选的填空式函数实现任务：我们首先让工具从官方仓库中提议候选函数，再经仔细人工筛选以选出核心3D几何组件。针对每个目标，我们生成多样化的边界单元测试，从而实现全自动、可复现的评分。我们评估了八个代表性开源与闭源模型以反映当前生态。最佳模型GPT-5仅达到36.6%的通过率，揭示了当前能力与可靠3D科学编码之间的巨大差距。GeoCodeBench将任务组织为两级层次：通用3D能力（几何变换与力学/光学公式化）与研究能力（新颖算法实现与几何逻辑路由）。这些轴上的得分呈正相关，但研究导向的任务明显更难。上下文消融进一步表明“更多论文文本”并不总是更好：在方法部分截断在统计上优于全文输入，凸显了长上下文科学理解中尚未解决的挑战。综上，这些发现使GeoCodeBench成为从通用编码迈向可信3D几何视觉编码的严谨测试平台。
英文原文摘要 1714 字符
AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our community would change substantially. To measure progress toward that goal, we introduce GeoCodeBench, a PhD-level benchmark that evaluates coding for 3D vision. Each problem is a fill-in-the-function implementation task curated from representative papers at recent venues: we first let a tool propose candidate functions from official repositories, then perform careful human screening to select core 3D geometric components. For every target, we generate diverse, edge-case unit tests, enabling fully automatic, reproducible scoring. We evaluate eight representative open- and closed-source models to reflect the current ecosystem. The best model, GPT-5, attains only 36.6% pass rate, revealing a large gap between current capabilities and dependable 3D scientific coding. GeoCodeBench organizes tasks into a two-level hierarchy: General 3D capability (geometric transformations and mechanics/optics formulation) and Research capability (novel algorithm implementation and geometric logic routing). Scores are positively correlated across these axes, but research-oriented tasks are markedly harder. Context ablations further show that "more paper text" is not always better: cutting off at the Method section statistically outperforms full-paper inputs, highlighting unresolved challenges in long-context scientific comprehension. Together, these findings position GeoCodeBench as a rigorous testbed for advancing from generic coding to trustworthy 3D geometric vision coding.