Base Model | OpenRouter | Announcement
## Introduction Ling-3.0-flash-Fin is the first finance-enhanced model in the Ant Ling family. Developed by Ant Group with leading financial institutions and domain experts, it extends [Ling-3.0-flash](https://huggingface.co/inclusionAI/Ling-3.0-flash) through continued training on high-quality financial data. With 124B total parameters, 5.1B activated parameters, and a 256K context window, the model combines financial expertise with efficient inference for long-horizon agent workflows. ### Highlights + **End-to-end financial research:** connects information retrieval, evidence review, calculation, modeling, and report preparation instead of treating them as isolated tasks. + **Source-grounded financial search:** Prioritizes authoritative sources to deliver accurate, complete, and traceable answers; [FinFIRST](https://huggingface.co/datasets/inclusionAI/FinFIRST) is open-sourced alongside the model to enable transparent evaluation of these capabilities. + **Multi-document financial reasoning:** reconciles reporting periods, definitions, assumptions, and conflicting figures across annual reports, earnings releases, regulatory filings, and research materials. + **Valuation and spreadsheet workflows:** understands formulas, actual-versus-estimate updates, cross-sheet dependencies, balance checks, scenario analysis, and editable financial-model delivery. + **Research-ready outputs:** organizes facts, analysis, judgments, and charts into clear, reviewable materials for further editing and professional review. ## Evaluation Ling-3.0-flash-Fin was evaluated across [FinFIRST](https://huggingface.co/datasets/inclusionAI/FinFIRST), FinSearchComp Verified, FinCRAFT, Finance Agent, APEX-Agents, SpreadsheetBench, and τ³-Banking. These benchmarks cover source-grounded retrieval, investment research, long-horizon execution, valuation modeling, spreadsheet operations, and banking workflows. The model is competitive with both similarly sized models and substantially larger general-purpose models, with particular strength in source selection and tool-intensive financial tasks.
## Local Serving
The current checkpoint is released in BF16. Because Ling-3.0-flash-Fin shares the same architecture as Ling-3.0-flash, it is compatible with the same SGLang and vLLM runtimes. For deployment instructions, see the [Ling-3.0-flash deployment guide](https://huggingface.co/inclusionAI/Ling-3.0-flash#quickstart).
> **Important:** Thinking mode is enabled by default. For optimal performance, we strongly recommend using `temperature=1.0`, `top_p=0.95`, and `top_k=20` for general inference.
>
## Limitations and Future Work
As our first finance-enhanced release, Ling-3.0-flash-Fin still requires further validation in complex, long-horizon workflows. Key assumptions, valuation results, and investment conclusions require professional review and do not constitute investment advice.
Future releases will explore finance-enhanced models at larger scales to further improve complex reasoning and long-horizon task execution.
## Training content summary
The public training-content summary identifying **Ling-3.0-flash-Fin** is available below. Please refer to the document for its covered model versions, training-content scope, summary version, and update date.
- [Training-content summary (PDF)](https://huggingface.co/inclusionAI/AI-Transparency/resolve/main/Ling-3.0-LLM_TDS-Summary.pdf)
- [Training-content documentation index](https://huggingface.co/inclusionAI/AI-Transparency)
This summary concerns training-content disclosure; it does not replace the model’s technical documentation, usage terms, or license.