Related papers: CRUXEval: A Benchmark for Code Reasoning, Understa…

In modern software development, developers frequently need to understand code behavior at a glance -- whether reviewing pull requests, debugging issues, or navigating unfamiliar codebases. This ability to reason about dynamic program…

In this work, we introduce CodeRepoQA, a large-scale benchmark specifically designed for evaluating repository-level question-answering capabilities in the field of software engineering. CodeRepoQA encompasses five programming languages and…

Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three major imbalances: 85.7% focus on a single programming…

Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM responses. As LLMs are increasingly used as programmer…

LLMs have become the go-to choice for code generation tasks, with an exponential increase in the training, development, and usage of LLMs specifically for code generation. To evaluate the ability of LLMs on code, both academic and industry…

This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we believe to be the most extensive unified cybersecurity safety…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks primarily assess functional correctness and neglect broader…

Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet. Programming benchmarks, typically consisting of buggy code snippet and their…

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve…

Increase in computational scale and fine-tuning has seen a dramatic improvement in the quality of outputs of large language models (LLMs) like GPT. Given that both GPT-3 and GPT-4 were trained on large quantities of human-generated text, we…

Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings. This paper investigates efficient CoT…

Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating…

The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its…

We introduce a new type of programming challenge called programming puzzles, as an objective and comprehensive evaluation of program synthesis, and release an open-source dataset of Python Programming Puzzles (P3). Each puzzle is defined by…

Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to…

Large language models (LLMs) have shown remarkable performance on various tasks, but existing evaluation benchmarks are often static and insufficient to fully assess their robustness and generalization in realistic scenarios. Prior work…

During early stages of CPU design, benchmarks can only run on simulators to evaluate CPU performance. However, most big data benchmarks are too huge at code size scale, which causes them to be unable to finish running on simulators at an…

Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a small number of metrics. The analysis of the evaluation…

Large language models achieve near-ceiling performance on code generation benchmarks, yet most of the programming languages used by popular benchmarks such as SWE-bench and HumanEval (e.g. Python, JavaScript) are squarely in-distribution.…

We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied…