# AI4Bharat, a research lab at Indian Institute of Technology (IIT) Madras, has introduced a new, open-source benchmark test specifically designed to assess the performance of large language models.

*genai · news · 2025-11-12 · The Indian Express*

## Key points

- AI4Bharat at IIT Madras launched Indic LLM-Arena, a benchmark for Indian languages in LLMs.
- The Indic LLM-Arena benchmark assesses large language models' performance on Indian context and safety.
- Google Cloud supported the development of this open-source, crowd-sourced benchmarking platform.
- This benchmark specifically addresses gaps in evaluating AI models for Indian languages and scenarios.

**Companies:** Google Cloud, Indian Institute of Technology (IIT) Madras
**Countries:** India

[Read the full story on The Indian Express](https://indianexpress.com/shorts/technology/artificial-intelligence/iit-madras-ai4bharat-benchmark-ai-indian-languages-10360996/)

---

Canonical: https://newsio.io/n/7a508ea8-70f6-4166-a8c9-916e6f888556/ai4bharat-a-research-lab-at-indian-institute-of-technology-iit-madras-has-introd
Summarized by Newsio from The Indian Express. https://newsio.io/how-it-works