DyCodeEval

What is DyCodeEval?

DyCodeEval introduces methods to generate dynamic evaluation dataset and metric. Using multi-agent cooperation to rewrite benchmarks at evaluation time, it…

Released

2025-06-23

Evaluates

强推理, Strong Reasoning, 推理, Reasoning, 代码, Code, Dynamic Benchmarking, ICML 2025, 大语言模型, LLM, 逻辑推理, 代码工程, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/DyCodeEval

DyCodeEval paper and code

• Paper https://arxiv.org/pdf/2503.04149
• Code https://github.com/SeekingDream/DyCodeEval

Which sources cite DyCodeEval?

• DyCodeEval

Related 强推理, Strong Reasoning, 推理, Reasoning, 代码, Code, Dynamic Benchmarking, ICML 2025, 大语言模型, LLM, 逻辑推理, 代码工程, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench