这篇论文搞了个InterFLOPBench，专门测LLM找C语言浮点bug。Qwen 3和Gemini 2.5等模型表现最强，F1超0.88。写代码的必看！
论文发布了InterFLOPBench，一个包含90个C语言内核和1130个测试样本的浮点错误分类基准。它评估了14个LLMs在六类错误（抵消、比较、除以零、溢出、下溢、NaN）上的多标签分类性能。结果显示，Qwen 3 32b、Gemini 2.5 Flash、Phi 4 Reasoning、DeepSeek R1T2和gpt-oss（20b和120b）等模型总体F1分数超过0.88。不同错误类别表现差异大：除以零平均F1为0.8479，而下溢和抵消分别只有0.6059和0.6164。
Benchmarking Large Language Models on Floating-Point Error Classification
This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We introduce InterFLOPBench, a benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs. The evaluation framework treats floating-point error detection as a multi-label classification problem and employs the F1-score metric to measure performance. Results demonstrate that latest models (Qwen 3 32b, Gemini 2.5 Flash, Phi 4 Reasoning, DeepSeek R1T2, and gpt-oss 20b and 120b) achieve a performance greater than 0.88 overall F1-score. Performance varies between error categories, between explicit operations such as division by zero (Average F1-score: 0.8479) and more subtle numerical phenomena such as underflow (Average F1-score: 0.6059) and cancellation (Average F1-score: 0.6164).