BigCodeBench

What is BigCodeBench?

BigCodeBench is a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks.

Released

2024-06-22

Evaluates

强推理, Strong Reasoning, 代码, Code, 大语言模型, LLM, 逻辑推理, Reasoning, 代码工程, 开源收录, Open-Source, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

BigCodeBench paper, code and dataset

• Paper https://arxiv.org/abs/2406.15877
• Code https://github.com/bigcode-project/bigcodebench
• Dataset https://huggingface.co/datasets/bigcode/bigcodebench

Which sources cite BigCodeBench?

• BigCodeBench

Related 强推理, Strong Reasoning, 代码, Code, 大语言模型, LLM, 逻辑推理, Reasoning, 代码工程, 开源收录, Open-Source, 不支持, Unsupported benchmarks

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