ToolVQA: A Benchmark for Visual Question Answering with External Tools

ToolVQA is a dataset introduced at ICCV 2025 for evaluating real-world tool-use capabilities in Large Foundation Models. The dataset is hosted on Hugging Face by author DietCoke4671 and was last updated on August 16, 2025. It is designed to address gaps in existing benchmarks for tool-augmented Visual Question Answering.

Use Cases

• Benchmarking the real-world tool-use performance of Large Foundation Models based on the dataset's stated purpose
• Training models for multimodal reasoning that requires external tool integration as described in the introduction
• Evaluating gaps in visual question answering when augmented with tools, as referenced in the dataset description

Strengths

• Dataset is associated with a peer-reviewed conference (ICCV 2025), suggesting academic rigor
• Last update timestamp is precise (2025 08 16 15:32:28), indicating recent maintenance

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download
• Column-level documentation is absent; field semantics must be inferred after download
• Row count, file formats, and license information are unknown, which may limit suitability assessment

Provenance

Source

Hugging Face, uploaded by DietCoke4671

Collection Method

Method of data gathering is not described in the provided input.

Time Range

Temporal coverage is not specified in the provided input.

Freshness

Last updated 2025-08-16 15:32:28

Geography

Spatial coverage is not specified in the provided input.