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
View all 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/Shrutam-2
Automatic Speech Recognition • Updated • 111 • 20
bharatgenai/Param2-17B-A2.4B-Thinking
Text Generation • 17B • Updated • 29.7k • 73
bharatgenai/AyurParam
Text Generation • 3B • Updated • 525 • 23
bharatgenai/sooktam2
Text-to-Speech • Updated • 1.25k • 37
bharatgenai/Param-1-2.9B-Instruct
Text Generation • 3B • Updated • 535 • 19
bharatgenai/FinanceParam
Text Generation • 3B • Updated • 719 • 9
bharatgenai/LegalParam
Text Generation • 3B • Updated • 360 • 10
bharatgenai/AgriParam
Text Generation • 3B • Updated • 204 • 11
bharatgenai/Param-1
Text Generation • Updated • 425 • 7
bharatgenai/Param-1-7B
7B • Updated • 213 • 4
datasets 7
bharatgenai/IndicParam
Viewer • Updated • 13.2k • 239 • 7
bharatgenai/ParamBench
Viewer • Updated • 17.3k • 21 • 5
bharatgenai/TORQUE
Viewer • Updated • 210 • 47 • 1
bharatgenai/BhashaBench-Legal
Viewer • Updated • 24.4k • 77 • 4
bharatgenai/BhashaBench-Finance
Viewer • Updated • 19.4k • 97 • 6
bharatgenai/BhashaBench-Krishi
Viewer • Updated • 15.4k • 35 • 8
bharatgenai/BhashaBench-Ayur
Viewer • Updated • 15k • 118 • 9