Decimal Point Analytics Launches Bindu FRS 1.0 - India's First GenAI Model Purpose-Built for Financial Statement Analysis and Standardisation, Delivering 98.79% First-Pass Accuracy

Distilled model achieves 77% reduction in first-pass errors versus frontier commercial LLMs on financial statement mapping, with continuous self-improvement and no per-query costs - purpose-built for data aggregators, rating agencies, and research providers

MUMBAI, India and NEW YORK and LONDON, May 26, 2026 /PRNewswire/ -- Decimal Point Analytics today launched Bindu FRS 1.0, a proprietary, distilled GenAI model built in India and engineered specifically for the analysis and standardisation of company financial statements - the first such model launched out of India for this category. In controlled testing across 100+ company filings - including annual, quarterly, and half-yearly reports from UK and Canadian issuers - the model delivered 98.79% first-pass accuracy and a 77% reduction in errors versus a frontier commercial LLM baseline, with continuous improvement from analyst corrections and no per-query licensing costs.

Bindu FRS 1.0 represents a new category of Indian AI capability - the country's first vertical, domain-specialised GenAI model engineered specifically for the task of converting unstructured financial disclosures into standardised, machine-readable data - and is operational today across DPA's managed data services for global financial data aggregators, rating agencies, and research providers.

For firms processing thousands of financial filings, this combines three structural advantages frontier commercial LLMs cannot match: domain specialization, self-improvement from corrections, and flat unit economics at scale.

Availability

Bindu FRS 1.0 is available for evaluation through a Free Accuracy Benchmark - prospects ship 50-100 of their own historical filings, receive a side-by-side comparison against their current workflow within six weeks. Private technical briefings available under NDA. https://decimalpointanalytics.com/contact-us

Shailesh Dhuri, CEO, Decimal Point Analytics, said: 

"Frontier commercial LLMs are extraordinary general-purpose tools. But for high-volume, high-accuracy, closed-domain work - like mapping the financial disclosures of tens of thousands of companies - general-purpose is the wrong architecture. Bindu FRS 1.0 is our answer: narrow scope, deep specialization, continuous improvement, and our data as the moat."

Shyam Pardeshi, Chief Solutions Officer, Decimal Point Analytics, added:

"Commercial LLMs hallucinate most on the data points that matter most - the newly reported, non-standard line items in real company filings. Bindu FRS 1.0 removes that failure mode by narrowing the model's world to a single well-bounded task and teaching it from corrections, not from scale."

About Decimal Point Analytics

Decimal Point Analytics is an AI-native digital transformation company headquartered in Mumbai, serving financial services, healthcare, CPG, and manufacturing clients across North America, India, the GCC, the UK, and Europe. DPA's capabilities span data & AI, digital modernization, cloud migration, workflow automation, and managed data operations. The company is a recipient of the Aegis Graham Bell Award for Innovation in GenAI - BFSI.

Note on methodology

Performance testing was conducted on 100+ company financial filings from UK and Canadian issuers, comprising 30 annual reports, 40 quarterly reports, and 30 half-yearly reports. Detailed model architecture, training methodology, and continuous learning mechanisms are proprietary to Decimal Point Analytics. Qualified prospects can request a private technical briefing under NDA.

https://decimalpointanalytics.com/contact-us

Logo: https://mma.prnewswire.com/media/2985425/Decimal_Point_Analytics_Logo.jpg

SOURCE Decimal Point Analytics (DPA)