BhashaBench-V1 is a domain-specific, multi-task, multilingual benchmark designed to evaluate large language models in India-centric contexts.
AI & ML interests
None defined yet.
Recent Activity
Papers
IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages
AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
models 15
bharatgenai/Param2-17B-A2.4B-Thinking
Text Generation • 17B • Updated • 4.41k • 58
bharatgenai/sooktam2
Text-to-Speech • Updated • 1.19k • 25
bharatgenai/Param-1-2.9B-Instruct
Text Generation • 3B • Updated • 631 • 19
bharatgenai/Shrutam-2
Automatic Speech Recognition • Updated • 8
bharatgenai/AyurParam
Text Generation • 3B • Updated • 1.35k • 17
bharatgenai/FinanceParam
Text Generation • 3B • Updated • 68 • 5
bharatgenai/LegalParam
Text Generation • 3B • Updated • 108 • 7
bharatgenai/AgriParam
Text Generation • 3B • Updated • 283 • 7
bharatgenai/Param-1
Text Generation • Updated • 140 • 7
bharatgenai/Param-1-7B
7B • Updated • 62 • 2
datasets 7
bharatgenai/IndicParam
Viewer • Updated • 13.2k • 84 • 6
bharatgenai/ParamBench
Viewer • Updated • 17.3k • 19 • 4
bharatgenai/TORQUE
Viewer • Updated • 210 • 114 • 1
bharatgenai/BhashaBench-Legal
Viewer • Updated • 24.4k • 249 • 4
bharatgenai/BhashaBench-Finance
Viewer • Updated • 19.4k • 183 • 2
bharatgenai/BhashaBench-Krishi
Viewer • Updated • 15.4k • 182 • 8
bharatgenai/BhashaBench-Ayur
Viewer • Updated • 15k • 161 • 9