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
10
bharatgenai/Param-1-2.9B-Instruct
Text Generation
•
3B
•
Updated
•
1.11k
•
16
bharatgenai/Shrutam-HindiASR-1.0
Automatic Speech Recognition
•
Updated
•
5
bharatgenai/AyurParam
Text Generation
•
3B
•
Updated
•
883
•
14
bharatgenai/LegalParam
3B
•
Updated
•
321
•
5
bharatgenai/Param-1
Text Generation
•
Updated
•
58
•
6
bharatgenai/FinanceParam
3B
•
Updated
•
124
•
5
bharatgenai/AgriParam
3B
•
Updated
•
141
•
7
bharatgenai/patram-7b-instruct
Image-Text-to-Text
•
8B
•
Updated
•
66
•
29
bharatgenai/sooktam-HindiTTS-0.5
Updated
•
4
bharatgenai/TTS-Hindi-0.5
Updated
•
1
datasets
7
bharatgenai/IndicParam
Viewer
•
Updated
•
13.2k
•
64
•
6
bharatgenai/ParamBench
Viewer
•
Updated
•
17.3k
•
6
•
4
bharatgenai/TORQUE
Viewer
•
Updated
•
210
•
168
•
1
bharatgenai/BhashaBench-Legal
Viewer
•
Updated
•
24.4k
•
127
•
4
bharatgenai/BhashaBench-Finance
Viewer
•
Updated
•
19.4k
•
146
•
2
bharatgenai/BhashaBench-Krishi
Viewer
•
Updated
•
15.4k
•
112
•
6
bharatgenai/BhashaBench-Ayur
Viewer
•
Updated
•
15k
•
78
•
8