Indian Multilingual Vision-Language Evaluation Dataset

IndicMMVet is a dataset for evaluating Large Vision-Language Models on Visual Question Answering tasks, created by krutrim-ai-labs. It focuses on integrated capabilities and multilingual content, specifically for Indian contexts. The dataset was last updated on March 5, 2025.

Use Cases

• Benchmark LVLMs on Visual Question Answering tasks using Indian multilingual content.
• Evaluate model performance on the integration of multiple core capabilities as defined by the dataset creators.
• Assess multilingual visual understanding for models targeting Indian languages and contexts.

Strengths

• Dataset is specifically designed for evaluating integrated capabilities in Vision-Language Models.
• Focuses on multilingual content relevant to India.
• Last updated on March 5, 2025, indicating recent maintenance.

Limitations

• No sample data, column information, or size details are available for assessment.
• The specific number of questions, images, or language pairs is unknown.
• Limited descriptive information is provided in the input.

Provenance

Source

krutrim-ai-labs

Collection Method

Designed for evaluating Large Vision-Language Models; specific collection method unknown.

Freshness

Last updated 2025-03-05.

Geography

India