Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem

About

We present FiMI (Finance Model for India), a domain-specialized financial language model developed by National Payments Corporation of India (NPCI) for Indian digital payment systems. We develop two model variants: FiMI Base and FiMI Instruct. FiMI adapts the Mistral Small 24B architecture through a multi-stage training pipeline, beginning with continuous pre-training on 68 Billion tokens of curated financial, multilingual (English, Hindi, Hinglish), and synthetic data. This is followed by instruction fine-tuning and domain-specific supervised fine-tuning focused on multi-turn, tool-driven conversations that model real-world workflows, such as transaction disputes and mandate lifecycle management. Evaluations reveal that FiMI Base achieves a 20\% improvement over the Mistral Small 24B Base model on finance reasoning benchmark, while FiMI Instruct outperforms the Mistral Small 24B Instruct model by 87\% on domain-specific tool-calling. Moreover, FiMI achieves these significant domain gains while maintaining comparable performance to models of similar size on general benchmarks.

Aboli Kathar, Aman Kumar, Anusha Kamath, Araveeti Srujan, Ashish Sharma, Chandra Bhushan, Divya Sorate, Duddu Prasanth Kumar, Evan Acharya, Harsh Sharma, Hrithik Kadam, Kanishk Singla, Keyur Doshi, Kiran Praveen, Kolisetty Krishna SK, Krishanu Adhikary, Lokesh MPT, Mayurdeep Sonowal, Nadeem Shaikh, Navya Prakash, Nimit Kothari, Nitin Kukreja, Prashant Devadiga, Rakesh Paul, Ratanjeet Pratap Chauhan, Raunak Kalani, Raviraj Joshi, Shamanth MH, Shantanu Pandey, Shubham Soni, Siddharth Dixit, Smriti Jopat, Sunil Patel, Suraj Singh, Suvradip Paul, Tulasi Pilla, Utkarsh Vaidya, Vineeth Nambiar, Vishal Kanvaty, Yatharth Dedhia• 2026

Related benchmarks

TaskDatasetResultRank
Code GenerationHumanEval
Pass@181.1
850
Multi-task Language UnderstandingMMLU
Accuracy77.99
842
Language UnderstandingMMLU
Accuracy72
756
Question AnsweringARC Challenge
Accuracy61.86
749
ReasoningBBH
Accuracy84.64
507
Mathematical ReasoningGSM8K
Accuracy (GSM8K)90.37
358
Instruction FollowingIFEval--
292
Question AnsweringTriviaQA
Accuracy52
210
Multitask Language UnderstandingMMLU-Pro
Accuracy59.88
99
ReasoningARC
Accuracy56
83
Showing 10 of 20 rows

Other info

Follow for update