Multiple-choice QA benchmarks usually evaluate small language models (SLMs) as direct answerers, but deployed language-model systems increasingly rely on external scaffolds such as tools, code, and repeated model calls. We introduce Code-Guided Reasoning (CGR), an evaluation protocol and generated-program resource for measuring when executable reasoning scaffolds improve SLM performance on MCQA tasks. CGR standardizes six components: a normalized item interface, a direct solver prompt, a generator prompt, a Python scaffold, solver-call and extraction helpers, and a three-channel result record. On 20,498 retained result rows from a locally prepared MCQA bundle and six metadata-registered solver models, the observed non-zero-baseline partition shows 66.21% macro assisted accuracy versus 38.11% direct accuracy, a +28.10 percentage-point difference with a pair-bootstrap interval of [20.32, 36.43]. Under a stricter Ab > 30% direct-signal gate, the macro difference is +14.11 points. These estimates are descriptive. Assisted inference uses a larger solver-call budget, answer extraction is brittle, Time-MQA contains the observed regressions, and some generated programs violate the no-hard-coding instruction. CGR provides the trace package needed to interpret these results, including direct, assisted, and generator-side answers, partition definitions, generated programs, response metadata, and audits.

翻译：多项选择问答基准测试通常将小型语言模型（SLM）作为直接作答者进行评估，但已部署的语言模型系统日益依赖外部框架，如工具、代码和多次模型调用。我们提出代码引导推理（CGR），这是一种评估协议和生成程序资源，用于衡量可执行推理框架在MCQA任务中提升SLM性能的效果。CGR标准化了六个组件：归一化题目接口、直接求解提示、生成提示、Python框架、求解器调用与提取辅助模块，以及三通道结果记录。基于本地准备的MCQA数据包中的20,498条保留结果行和六个元数据注册的求解器模型，在观察到的非零基线分区中，宏平均辅助准确率为66.21%，直接准确率为38.11%，差异为+28.10个百分点，配对自助法区间为[20.32, 36.43]。在更严格的Ab > 30%直接信号阈值下，宏平均差异为+14.11个百分点。这些估计为描述性统计。辅助推理使用了更大的求解器调用预算，答案提取具有脆弱性，Time-MQA中观察到性能退化，且部分生成程序违反了禁止硬编码指令。CGR提供了解释这些结果所需的追踪包，包括直接答案、辅助答案和生成器侧答案、分区定义、生成程序、响应元数据及审计信息。