# How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective

arXiv: https://arxiv.org/abs/2510.08720 · HTML: https://mlsanity.com/paper/2510.08720/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding](https://mlsanity.com/paper/2503.02951/) (2025)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [o1-Coder: an o1 Replication for Coding](https://mlsanity.com/paper/2412.00154/) (2024)
- [LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs](https://mlsanity.com/paper/2504.14655/) (2025)
- [Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning](https://mlsanity.com/paper/2506.03136/) (2025)
- [TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark](https://mlsanity.com/paper/2410.00752/) (2024)
- [CodeContests+: High-Quality Test Case Generation for Competitive Programming](https://mlsanity.com/paper/2506.05817/) (2025)
- [ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers](https://mlsanity.com/paper/2305.14591/) (2023)
- [Preference Optimization for Reasoning with Pseudo Feedback](https://mlsanity.com/paper/2411.16345/) (2024)
- [Z1: Efficient Test-time Scaling with Code](https://mlsanity.com/paper/2504.00810/) (2025)
- [CodeDPO: Aligning Code Models with Self Generated and Verified Source Code](https://mlsanity.com/paper/2410.05605/) (2024)
- [TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?](https://mlsanity.com/paper/2412.02883/) (2024)
- [Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models](https://mlsanity.com/paper/2505.14810/) (2025)
- [HardTests: Synthesizing High-Quality Test Cases for LLM Coding](https://mlsanity.com/paper/2505.24098/) (2025)
- [Towards Effective Code-Integrated Reasoning](https://mlsanity.com/paper/2505.24480/) (2025)
- [Process-Supervised Reinforcement Learning for Code Generation](https://mlsanity.com/paper/2502.01715/) (2025)
- [Rethinking Verification for LLM Code Generation: From Generation to Testing](https://mlsanity.com/paper/2507.06920/) (2025)
- [Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure](https://mlsanity.com/paper/2506.12278/) (2025)
- [B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests](https://mlsanity.com/paper/2409.08692/) (2024)
- [Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems](https://mlsanity.com/paper/2506.06821/) (2025)
- [Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning](https://mlsanity.com/paper/2508.05710/) (2025)
- [ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search](https://mlsanity.com/paper/2508.19576/) (2025)

## Built on by (most cited first, 4 of 4)

- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)
- [Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration](https://mlsanity.com/paper/2511.15351/) (2025)
- [VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2511.16077/) (2025)
- [Efficient RLVR Training via Weighted Mutual Information Data Selection](https://mlsanity.com/paper/2603.01907/) (2026)

## Abstract (arXiv)

Evaluating test cases automatically generated by Large Language Models (LLMs) is a critical yet challenging task. Existing benchmarks often evaluate the exclusion ratio on large, unstructured collections of wrong codes, suffering from high computational costs and score inflation. Furthermore, they inadvertently reward generators that detect common, trivial bugs, while failing to penalize their inability to identify rare yet critical faults. In this work, we connect two fundamental questions: (1) What is the minimal set of wrong codes sufficient to represent the entire error space? and (2) What is the minimal set of test cases needed to distinguish them? We introduce a novel framework that formalizes benchmark construction as finding an optimal diagnostic basis in a binary code-test matrix, where rows represent wrong codes and columns represent test case results. The rank of this matrix specifies the minimal number of independent error patterns (wrong codes) and provides a tight upper bound on the number of test cases required for complete fault coverage. Our objective is to identify a basis of size equal to the matrix rank that maximizes internal diversity. To tackle this NP-hard problem, we propose WrongSelect, an efficient approximation algorithm to select maximally diverse wrong codes. Applying this framework to millions of competitive programming submissions, we construct TC-Bench, a compact, diverse, and inflation-resistant benchmark. Extensive experiments show that even the most advanced test case generation methods achieve only ~60% exclusion rates on TC-Bench, exposing a significant gap in their diagnostic power and highlighting substantial room for future improvement. Our dataset is available at: https://huggingface.co/datasets/Luoberta/TC-Bench and our code is at: https://github.com/Luowaterbi/TC-Bench.