CLEVER Benchmark

What is CLEVER?

CLEVER is a benchmark suite for end-to-end code generation and formal verification in Lean 4, adapted from the HumanEval dataset. It requires models to…

Released

2025-05-20

Evaluates

代码, Code, 科学智能, AI for Science, 代码工程, 科学推理, Scientific Reasoning, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

CLEVER paper, code and dataset

• Paper https://arxiv.org/abs/2505.13938
• Code https://github.com/trishullab/clever
• Dataset https://huggingface.co/datasets/amitayusht/clever

Which sources cite CLEVER?

• CLEVER

Related 代码, Code, 科学智能, AI for Science, 代码工程, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard