Ling-3.0-flash-Fin Takes Auditable Tool Chains Into Financial Work
- Source
- Ant Ling
- Date
Financial work depends on trustworthy sources, consistent definitions, accurate calculations and auditable outputs. Introducing Ling-3.0-flash-Fin, a finance-enhanced version of Ling-3.0-flash, developed with financial institutions and domain experts. With 124B total and 5.1B active parameters, it supports information retrieval, research, valuation modeling and report preparation across long reports, research materials and complex workbooks. The model showed competitive results across FinFIRST, FinSearchComp Verified, FinCRAFT, FinanceAgent v1.1/v2, APEX-Agents, SpreadsheetBench v1/v2 and τ³-Banking. We will open-source the model weights next week.
Financial expertise also needs a strong general foundation. Ling-3.0-flash-Fin scored 41 on AA Intelligence Index v4.1.1, compared with 38 for Ling-3.0-flash. The result reflects an improvement in broader model capabilities alongside its financial specialization.
Demo 1 | Financial Search The model reconstructed four first disclosures of Google’s monthly token volume. Across 23 tool calls, it prioritized primary sources, reconciled definitions and dates, and calculated interval increases with a traceable evidence chain.
Demo 2 | Real Financial Research For Spire, 55 tool calls across 10-K, earnings releases and 8-K filings identified Storage as discontinued operations, rebuilt continuing-operations earnings and validated $17.8M in historical profit—while preserving the forecast boundary.
Context
Ant Ling introduces Ling-3.0-flash-Fin, a finance-enhanced version of Ling-3.0-flash developed with financial institutions and domain experts. The thread stresses trustworthy sources and auditable outputs. In one demonstration, the company says the model made 55 tool calls across a company's 10-K, earnings releases and 8-K filings to identify a discontinued segment, rebuild continuing-operations earnings and validate $17.8 million in historical profit while preserving the forecast boundary. In another, it says 23 tool calls reconstructed four first disclosures of Google's monthly volume from primary sources, reconciling definitions and dates.
Ant Ling also reports a score of 41 on Artificial Analysis Intelligence Index v4.1.1 against 38 for Ling-3.0-flash, which it reads as improved general capability alongside finance specialization. It says expert review remains essential for key assumptions, valuation outputs and investment conclusions, and that it planned to open-source the weights the following week. These are the company's own claims, the demo videos were not reviewed, and nothing here is financial advice.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Checking sign-in…
Loading comments…