Challenge: Existing large language models for software engineering rely on coarse-grained pass rates obscuring specific cognitive bottlenecks.
Approach: They propose a repository-level benchmark that dissects coding capabilities through atomized tasks.
Outcome: The proposed framework achieves a 78.55% validity yield, surpassing the 31.7% retention rate of SWE-bench-Verified.

Similar Papers

DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies highlight that dependency-related issues cause over 40% of observed runtime errors on the generated repository.
Approach: They propose a large-scale benchmark and evaluation framework specifically designed to assess LLMs’ capability on dependency inference.
Outcome: The proposed model achieves only a 48% execution pass rate on Python, indicating room for improvement.
RubricBench: Aligning Model-Generated Rubrics with Human Standards (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks lack discriminative complexity and ground-truth rubric annotations required for rigorous evaluation.
Approach: They propose a curated benchmark with 1,147 pairwise comparisons to assess the reliability of rubric-based evaluation.
Outcome: The proposed benchmarks show that they support diverse domains, exhibit discriminative ability, provide high-quality annotations, and include human-authored rubrics.
CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Copied to clipboard

Challenge: Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach: They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome: The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.
What can Large Language Models Capture about Code Functional Equivalence? (2025.findings-naacl)

Copied to clipboard

Challenge: SeqCoBench is a benchmark to assess how Code-LLMs can capture code semantics.
Approach: They propose a benchmark to assess how Code-LLMs capture code semantics . they use seqCoBench to evaluate whether they can discern semantically equivalent or different pairs of programs .
Outcome: The proposed benchmarks show that they can capture code semantics better than classical match-based retrieval scores.
CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction (2026.findings-acl)

Copied to clipboard

Challenge: Existing code reasoning benchmarks evaluate final output correctness under a single implementation.
Approach: They propose a Code Reasoning benchmark that evaluates code reasoning through implementation invariance and process transparency.
Outcome: The proposed benchmarks lack implementation invariance and process transparency . they observe superficial execution where models arrive at correct outputs without reasoning .
Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Copied to clipboard

Challenge: Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach: a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome: The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.
LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking (2024.eacl-demo)

Copied to clipboard

Challenge: Recent development and success of Large Language Models necessitate evaluation of their performance across diverse NLP tasks in different languages.
Approach: They propose a framework that can be customized to evaluate LLMs for any NLP task, regardless of language.
Outcome: The LLMeBench framework can be customized to evaluate LLMs for any NLP task, regardless of language.
MojoBench: Language Modeling and Benchmarks for Mojo (2025.findings-naacl)

Copied to clipboard

Challenge: Mojo is a programming language that has been praised for its speed and performance over Python.
Approach: They propose a framework for Mojo code generation that evaluates code Large Language Models (LLMs) they propose 'mojo-Coder' which is the first LLM pretrained and fine-tuned for MoJO code generation .
Outcome: MojoBench is the first framework for mojo code generation . it achieves a 30-35% performance improvement over leading models like GPT-4o and Claude-3.5-Sonnet .
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating the code understanding and generation capacities of Large Language Models are insufficient . existing benchmarks focus on a narrow range of popular programming languages and specific tasks .
Approach: They propose an execution-based, multilingual, multitask evaluation benchmark for LLMs . they evaluate coding performance from three dimensions: length, difficulty, efficiency .
Outcome: The proposed benchmark covers 43 programming languages and eight coding tasks.
XCodeEval: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
Approach: They propose to use a multilingual multitask benchmark to evaluate large language models that can generate codes from natural language descriptions, repair buggy codes, and translate between languages.
Outcome: The proposed model performs 7 tasks covering up to 11 languages with execution-level parallelism and 25 M document-level coding examples (16.5 B tokens)

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations