IndicGenBench sets a new standard for LLM performance across 29 Indic languages. This project promotes linguistic diversity in AI, which is crucial for its adoption globally. Key aspects include:

• Cross-lingual capabilities: Enabling tasks like summarization, translation, and QA across multiple languages.
• Human curated data: Ensures high-quality benchmarks.
• Technological inclusion: Bringing lesser-represented languages to the forefront in AI research.

This effort not only advances the capabilities of LLMs in handling diverse languages but also addresses the need for tailored AI applications in non-Western countries.