# Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval

arXiv: https://arxiv.org/abs/2502.19149 · HTML: https://mlsanity.com/paper/2502.19149/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 14 of 14)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [On Mitigating Code LLM Hallucinations with API Documentation](https://mlsanity.com/paper/2407.09726/) (2024)
- [DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation](https://mlsanity.com/paper/2408.13204/) (2024)
- [Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation](https://mlsanity.com/paper/2409.15895/) (2024)
- [Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2411.19463/) (2024)

## Built on by (most cited first, 3 of 3)

- [Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality](https://mlsanity.com/paper/2503.05860/) (2025)
- [Large Language Models for Multilingual Code Intelligence: A Survey](https://mlsanity.com/paper/2604.25960/) (2026)
- [Demystifying the Silence of Correctness Bugs in PyTorch Compiler](https://mlsanity.com/paper/2604.08720/) (2026)

## Abstract (arXiv)

Existing code generation benchmarks for Large Language Models (LLMs) such as HumanEval and MBPP are designed to study LLMs' end-to-end performance, where the benchmarks feed a problem description in natural language as input and examine the generated code in specific programming languages. However, the evaluation scores revealed in this way provide a little hint as to the bottleneck of the code generation -- whether LLMs are struggling with their problem-solving capability or language-coding capability. To answer this question, we construct PseudoEval, a multilingual code generation benchmark that provides a solution written in pseudocode as input. By doing so, the bottleneck of code generation in various programming languages could be isolated and identified. Our study yields several interesting findings. For example, we identify that the bottleneck of LLMs in Python programming is problem-solving, while Rust is struggling relatively more in language-coding. Also, our study indicates that problem-solving capability may transfer across programming languages, while language-coding needs more language-specific effort, especially for undertrained programming languages. Finally, we release the pipeline of constructing PseudoEval to facilitate the extension to existing benchmarks. PseudoEval is available at: https://anonymous.4open.science/r/PseudocodeACL25-7B74.