Benchmark Radar™
Star —

DynaMath Benchmark

Explore score history ↗

DynaMath is a dynamic visual math benchmark designed for in-depth assessment of VLMs. It includes 501 high-quality, multi-topic seed questions, each represented as a Python program enabling the automatic generation of a much larger set of concrete questions.

Publisher
University of Illinois at Urbana-Champaign (published the hub card)
Released
2024-10-29
Modality
multimodal
Evaluates
多模态, Multimodal, 推理, Reasoning, 数学, Math, 多模态模型, VLM, 逻辑推理, 数理能力
Openness
open
Importer
OpenCompass Hub

Source provenance

DynaMath paper, code and dataset

No reported scores are on record for this benchmark yet.

Which sources cite DynaMath?

Related 多模态, Multimodal, 推理, Reasoning, 数学, Math, 多模态模型, VLM, 逻辑推理, 数理能力 benchmarks