# An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks

arXiv: https://arxiv.org/abs/2609.18052 · HTML: https://mlsanity.com/paper/2609.18052/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 23 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [MathArena: Evaluating LLMs on Uncontaminated Math Competitions](https://mlsanity.com/paper/2505.23281/) (2025)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models](https://mlsanity.com/paper/2310.20410/) (2023)
- [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [Human vs Machine Mathematical Difficulty on Project Euler: An Experimental Analysis](https://mlsanity.com/paper/2606.21972/) (2026)

## Abstract (arXiv)

This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a mandated signature and data-transfer-object specification, crossing four model and agentic coding tool combinations with two prompt variants to yield eight configurations, with iteration forbidden and hardcoded answers explicitly prohibited. Eight problem statements were withheld to probe how models respond to missing input. The 7,593 resulting methods were classified by an eight-class outcome taxonomy describing what each does about producing an answer, then deployed and executed, giving 7,936 measured requests joined to that classification. Structural conformance approached ceiling, yet 38.4% of methods do not compute the value they returned and only 12.9% of returned answers were correct. Conditioning on outcome class shows that response reliability and correctness are inversely related, whereas genuinely computing methods answered least often and were correct 19.3%. Limitations include single generation runs per configuration, partial harness coverage, single-pass timing, syntactic classification, and probable corpus contamination.