Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy

Source

arXiv

arxiv.org/abs/2607.15176v1

Read the source

Source

Plain-Language Brief

Researchers evaluated six multimodal large language models (MLLMs) on a standardized scientific visualization literacy assessment test, consisting of 49 items based on 18 visualizations and illustrations. The study found that Gemini was the strongest model overall, while open-source models performed below the human baseline. Performance varied across techniques and tasks, with models excelling in scientific illustration, search, and spatial understanding but struggling with texture-based and integration-based visualizations and quantitative estimation.

What the Document Says

  • Six MLLMs were benchmarked on a SciVis literacy assessment test with 49 items based on 18 visualizations.
  • The study compared three closed-source models and three open-source models under a closed-world protocol.
  • Results showed that Gemini exceeded the human mean across evaluated subsets, while open-source models remained below the human baseline.
  • Performance was uneven across techniques and tasks, with models performing best on scientific illustration, search, and spatial understanding, but struggling with texture-based and integration-based visualizations and quantitative estimation.
  • Error analysis revealed recurring failures in fine-grained quantitative estimation, flow-direction interpretation, and grounded encoding interpretation.
  • The findings suggest that SciVis literacy is a necessary benchmark dimension for evaluating multimodal AI systems.

Key Concepts Mentioned

  • multimodal large language models
  • scientific visualization literacy assessment test
  • closed-source models
  • open-source models
  • human participants
  • Gemini
  • performance
  • techniques
  • tasks
  • error analysis

Claims Made by the Document

  • Current MLLMs do not exhibit uniform SciVis literacy.
  • Gemini is the strongest model overall.
  • Open-source models remain below the human baseline.

Evidence Used

  • Results show that current MLLMs do not exhibit uniform SciVis literacy.
  • Results show that Gemini exceeds the human mean across evaluated subsets.
  • Results show that open-source models remain below the human baseline.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis). We benchmark six MLLMs on the scientific visualization literacy assessment test, a standardized SciVis literacy assessment comprising 49 items based on 18 scientific visualizations and illustrations, spanning 8 techniques and 11 task types. We evaluate three closed-source and three open-source models under a closed-world protocol and compare their performance using data from 485 human participants. Results show that current MLLMs do not exhibit uniform SciVis literacy. Gemini is the strongest model overall, exceeding the human mean across the evaluated subsets, whereas the open-source models remain below the human baseline. Performance is highly uneven across techniques and tasks: models perform best on scientific illustration, search, and spatial understanding, but struggle on texture-based and integration-based visualizations and on quantitative estimation. Error analysis reveals recurring failures in fine-grained quantitative estimation, flow-direction interpretation, and grounded encoding interpretation. These findings position SciVis literacy as a necessary benchmark dimension for evaluating multimodal AI systems. Our code and model outputs are publicly available at https://github.com/patdmp/mllm-scivis-lit-benchmark.