ArtifactsBench

What is ArtifactsBench?

ArtifactsBench is a benchmark with 1,825 tasks for evaluating LLM-generated visual and interactive code. It addresses the gap of traditional benchmarks that…

Released

2025-07-01

Modality

multimodal

Evaluates

多模态, Multimodal, 推理, Reasoning, 代码, Code, ArtifactsBench, 代码可视化, 代码生成, 多模态模型, VLM, 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/ArtifactsBench

ArtifactsBench paper and code

• Paper https://arxiv.org/abs/2507.04952
• Code https://github.com/Tencent-Hunyuan/ArtifactsBenchmark

Which sources cite ArtifactsBench?

• ArtifactsBench

Related 多模态, Multimodal, 推理, Reasoning, 代码, Code, ArtifactsBench, 代码可视化, 代码生成, 多模态模型, VLM, 逻辑推理, 代码工程, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench