---
title: README
emoji: 📊
colorFrom: blue
colorTo: indigo
sdk: static
pinned: false
---

<p align="center"><img src="banner.png" alt="The Fin AI — benchmarks, models and leaderboards for finance" width="100%"/></p>

**The Fin AI** is a global academy advancing financial general intelligence through education, open research and incubation. This is where we release our **benchmarks, models, leaderboards and demos** for financial AI — across English, Chinese, Japanese, Spanish and Greek, and across text, vision and audio. 🌐 [thefin.ai](https://thefin.ai) · 📄 [all our papers](https://huggingface.co/collections/TheFinAI/the-fin-ai-papers-6ac71a0c9fe2bdb2946040b0)

### 🎯 Our vision

> **Open-source, trustworthy Financial General Intelligence** — pursued together by researchers, engineers and financial experts around the world. *AI Readiness in Finance.*

Three pillars, one mission:

| | |
|---|---|
| 🎓 **Education** | Bringing and educating the next generation of financial AI researchers and talents through courses, study groups and hands-on learning. |
| 🔬 **Research** | Driving rigorous and transparent research with open benchmarks, models and agent systems that advance the science of financial AI — **this Hugging Face organization is where that work is released.** |
| 🚀 **Incubation** | Transforming ideas into impactful financial AI solutions by supporting early-stage teams with guidance, resources and real-world use cases. |

🏅 Named one of Global Finance's *World's Best Financial Innovation Labs 2026*.

### News 🗞️

- **Oct 2026** · All leaderboards redesigned, with live data and a *last updated* date; the [Plutus-8B](https://huggingface.co/spaces/TheFinAI/plutus-8B-instruct) and [FinLLaVA](https://huggingface.co/spaces/TheFinAI/FinLLaVA) demos are back on ZeroGPU.
- **May 2026** · [Herculean](https://huggingface.co/collections/TheFinAI/herculean-agentic-financial-benchmark-6ac71541a7f8dd780d7ab3dd): agentic financial analysis — trading, hedging, reporting and auditing.
- **Mar 2026** · [EnterpriseArena](https://huggingface.co/collections/TheFinAI/enterprisearena-can-llm-agents-be-cfos-6ac7153d9ffaefeeb3a950d4): can LLM agents act as CFOs over long horizons?
- **Feb 2026** · [Ebisu](https://huggingface.co/collections/TheFinAI/ebisu-japanese-financial-evaluation-6ac7153a5be985dedba08c78) for Japanese financial language, and [Conv-FinRe](https://huggingface.co/collections/TheFinAI/conv-finre-conversational-financial-recommendation-69880c8328d2264727b74fb5) for conversational financial recommendation.
- **Nov 2025** · [FinCriticalED](https://huggingface.co/collections/TheFinAI/fincriticaled-fact-level-financial-ocr-6ac7153c3d632745cc3f7f01): fact-level OCR of financial documents.
- **Oct 2025** · [FinAuditing](https://huggingface.co/collections/TheFinAI/finauditing-taxonomy-structured-auditing-68e5f80606e22454027075e7) for taxonomy-structured auditing, and the live [Agent Market Arena](https://huggingface.co/spaces/TheFinAI/Agent-Market-Arena).

### 🏆 Leaderboards & demos

- [**Open FinLLM Leaderboard**](https://huggingface.co/spaces/TheFinAI/Open-FinLLM-Leaderboard) — MultiFinBen: 21 models on 36 datasets in five languages and three modalities.
- [**Reasoning Leaderboard**](https://huggingface.co/spaces/TheFinAI/open-finllm-reasoning-leaderboard) — Fino1: numerical reasoning over reports, long documents and XBRL.
- [**Greek Financial LLM Leaderboard**](https://huggingface.co/spaces/TheFinAI/Open-Greek-Financial-LLM-Leaderboard) — Plutus: five Greek financial tasks.
- [**Agent Market Arena**](https://huggingface.co/spaces/TheFinAI/Agent-Market-Arena) — LLM trading agents competing in live markets.
- [**IJCAI 2024 FinLLM Challenge**](https://huggingface.co/spaces/TheFinAI/IJCAI-2024-FinLLM-Leaderboard) — final results of the shared task.
- Demos: [**Plutus-8B**](https://huggingface.co/spaces/TheFinAI/plutus-8B-instruct) (Greek financial chat) · [**FinLLaVA**](https://huggingface.co/spaces/TheFinAI/FinLLaVA) (questions about charts and tables)

### 📊 Benchmarks

**Multilingual & multimodal**
- [**MultiFinBen**](https://huggingface.co/collections/TheFinAI/multifinben-multilingual-and-multimodal-financial-evaluation-6826f6fc4bc13d8af4fab223) — text, OCR and audio tasks in five languages ([arXiv:2506.14028](https://arxiv.org/abs/2506.14028))
- [**ICE-PIXIU**](https://huggingface.co/collections/TheFinAI/ice-pixiu-chinese-financial-evaluation-65e5851af7daaa71c1c59902) Chinese · [**FLARE-ES**](https://huggingface.co/collections/TheFinAI/flare-es-spanish-financial-evaluation-65e5855900680b19bc83e03d) Spanish · [**Plutus**](https://huggingface.co/collections/TheFinAI/plutus-greek-financial-evaluation-67bc718fb8d897c65f1e87db) Greek · [**Ebisu**](https://huggingface.co/collections/TheFinAI/ebisu-japanese-financial-evaluation-6ac7153a5be985dedba08c78) Japanese
- [**FinCriticalED**](https://huggingface.co/collections/TheFinAI/fincriticaled-fact-level-financial-ocr-6ac7153c3d632745cc3f7f01) — fact-level OCR of financial documents ([arXiv:2511.14998](https://arxiv.org/abs/2511.14998))

**Financial NLP, reasoning & risk**
- [**FinBen & PIXIU**](https://huggingface.co/collections/TheFinAI/finben-and-pixiu-english-financial-evaluation-658f515911f68f12ea193194) — holistic English evaluation: extraction, QA, summarization, forecasting, trading ([arXiv:2402.12659](https://arxiv.org/abs/2402.12659))
- [**CALM**](https://huggingface.co/collections/TheFinAI/calm-credit-scoring-and-risk-assessment-6ac7153781499dcd5001572e) — credit scoring, fraud, financial distress and claims ([arXiv:2310.00566](https://arxiv.org/abs/2310.00566))
- [**FMD**](https://huggingface.co/collections/TheFinAI/fmd-financial-misinformation-detection-6ac715408313fc0cb7529013) misinformation detection · [**Conv-FinRe**](https://huggingface.co/collections/TheFinAI/conv-finre-conversational-financial-recommendation-69880c8328d2264727b74fb5) conversational recommendation

**Filings, XBRL & auditing**
- [**FinTagging**](https://huggingface.co/collections/TheFinAI/fintagging-xbrl-tagging-68270132372c6608ac069bef) — XBRL tagging of financial reports ([arXiv:2505.20650](https://arxiv.org/abs/2505.20650))
- [**FinAuditing**](https://huggingface.co/collections/TheFinAI/finauditing-taxonomy-structured-auditing-68e5f80606e22454027075e7) — taxonomy-structured, multi-document auditing ([arXiv:2510.08886](https://arxiv.org/abs/2510.08886))

**Agents & decision-making**
- [**Herculean**](https://huggingface.co/collections/TheFinAI/herculean-agentic-financial-benchmark-6ac71541a7f8dd780d7ab3dd) ([arXiv:2605.14355](https://arxiv.org/abs/2605.14355)) · [**EnterpriseArena**](https://huggingface.co/collections/TheFinAI/enterprisearena-can-llm-agents-be-cfos-6ac7153d9ffaefeeb3a950d4) ([arXiv:2603.23638](https://arxiv.org/abs/2603.23638)) · [**Agent Market Arena**](https://huggingface.co/spaces/TheFinAI/Agent-Market-Arena) ([arXiv:2510.11695](https://arxiv.org/abs/2510.11695))

### 🧠 Models

- [**Fin-o1 / Fino1**](https://huggingface.co/collections/TheFinAI/fino1-fin-o1-financial-reasoning-682702bbd25a7ef4512df24d) — reasoning-enhanced financial LLMs, 8B and 14B ([arXiv:2502.08127](https://arxiv.org/abs/2502.08127))
- [**Open-FinLLMs**](https://huggingface.co/collections/TheFinAI/open-finllms-finllama-finllama-instruct-finllava-66b671f2b4958a65e20decbe) — FinLLaMA, FinLLaMA-Instruct and the multimodal FinLLaVA ([arXiv:2408.11878](https://arxiv.org/abs/2408.11878))
- [**Plutus-8B**](https://huggingface.co/TheFinAI/plutus-8B-instruct) — the first Greek financial LLM ([arXiv:2502.18772](https://arxiv.org/abs/2502.18772))
- [**FinSeer & StockLLM**](https://huggingface.co/collections/TheFinAI/finseer-retrieval-augmented-time-series-forecasting-6ac7153f1e8bbfa51e7bd031) — retrieval-augmented time-series forecasting ([arXiv:2502.05878](https://arxiv.org/abs/2502.05878))
- [**FinMA**](https://huggingface.co/collections/TheFinAI/finben-and-pixiu-english-financial-evaluation-658f515911f68f12ea193194) — the original PIXIU instruction-tuned models ([arXiv:2306.05443](https://arxiv.org/abs/2306.05443))

### ⚡ Quick start

Most datasets ask for a short form (name, affiliation, intended use) that is **approved automatically**. Accept it once on the dataset page, log in, and load:

```python
from datasets import load_dataset

ds = load_dataset("TheFinAI/en-fpb")  # FinBen · Financial PhraseBank sentiment
```

Datasets are named `{language}-{task}` — `en-fpb`, `zh-stocka`, `es-tsa`, `gr-qa`, `jp-icr`, `multi-…` for multilingual — while paper-named benchmarks keep their names (`FinCriticalED`, `Herculean`). Old names such as `flare-fpb` still redirect. Licenses follow the original sources and are stated on every card. To evaluate a model on our tasks, start from [FinBen](https://github.com/The-FinAI/FinBen) or [MultiFinBen](https://github.com/xueqingpeng/MultiFinBen).

### 🤝 Community

[Website](https://thefin.ai) · [GitHub](https://github.com/The-FinAI) · [Discord](https://discord.gg/Wpt347rusk) · [Google Groups](https://groups.google.com/g/the-fin-ai) · [YouTube](https://www.youtube.com/@TheFinAI-g6j/featured) · [Google Scholar](https://scholar.google.com/citations?hl=en&view_op=list_works&user=P3Mxb4kAAAAJ)

Questions about a dataset or model? Open a discussion on its page.