by open-compass · Agent Tool · ★ 21
CNFinBench: Evaluating Expertise, Autonomy, and Integrity in Finance Language: English | 中文。 📹 For clearer demo video, please click the link: Video https://github.com/user-attachments/assets/c15e95fb-8081-474b-936a-3686ac312c62 📣 News & Announcements 📰 Media Coverage 👉 CNFinBench Released: A New Benchmark for Financial LLM Safety Evaluation 👉 From Capabilities to Agents: How CNFinBench Evaluates Compliance and Safety of Financial LLMs 👉 Shanghai Government: Financial LLM Evaluation System 2.0 Released in Shanghai 👉 21st Century Business Herald: Industry Standards Upgraded! 2025...
| Stars | 21 |
| Forks | 1 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 59.0653104327017/100 |
| Last Updated | 2026-10-03 |
| Created | 2026-04-10 |
| Platforms | python |
| Est. Tokens | ~15k |
Explore other popular agent tool tools:
CNFinBench is CNFinBench — the first comprehensive benchmark for high-stakes financial scenarios. It spans 29 subtasks grounded in authoritative financial corpora and real business contexts, reconstructing end-to-e. It is categorized as a Agent Tool with 21 GitHub stars.
CNFinBench is primarily written in Python.
You can find installation instructions and usage details in the CNFinBench GitHub repository at github.com/open-compass/CNFinBench. The project has 21 stars and 1 forks, indicating an active community.