# Benchmarking PhD-Level Coding in 3D Geometric Computer Vision

arXiv: https://arxiv.org/abs/2603.30038 · HTML: https://mlsanity.com/paper/2603.30038/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 80 of its 84 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 30 of 80)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [MLVU: Benchmarking Multi-task Long Video Understanding](https://mlsanity.com/paper/2406.04264/) (2024)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM](https://mlsanity.com/paper/2402.09181/) (2024)
- [MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving](https://mlsanity.com/paper/2307.15058/) (2023)
- [OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web](https://mlsanity.com/paper/2402.17553/) (2024)
- [MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation](https://mlsanity.com/paper/2208.08227/) (2022)
- [CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark](https://mlsanity.com/paper/2409.11363/) (2024)
- [How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs](https://mlsanity.com/paper/2311.16101/) (2023)
- [3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting](https://mlsanity.com/paper/2412.12507/) (2024)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing](https://mlsanity.com/paper/2412.15867/) (2024)
- [SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories](https://mlsanity.com/paper/2409.07440/) (2024)
- [Fast Feedforward 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2410.08017/) (2024)
- [PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology](https://mlsanity.com/paper/2401.16355/) (2024)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [Reflective Gaussian Splatting](https://mlsanity.com/paper/2412.19282/) (2024)
- [SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing](https://mlsanity.com/paper/2403.19615/) (2024)
- [DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds](https://mlsanity.com/paper/2503.18402/) (2025)
- [LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes](https://mlsanity.com/paper/2410.14462/) (2024)
- [THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models](https://mlsanity.com/paper/2405.05256/) (2024)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2503.12772/) (2025)

## Built on by (most cited first, 2 of 2)

- [PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation](https://mlsanity.com/paper/2607.01883/) (2026)
- [PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides](https://mlsanity.com/paper/2609.29718/) (2026)

## Abstract (arXiv)

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.