# CNFinBench

Tests Chinese financial LLMs on expertise, agentic autonomy and integrity (safety and compliance).

## Facts

- Maker: Shanghai AI Laboratory (OpenCompass)
- Year: 2025
- Use case: Finance knowledge
- Size: 11,947 single-turn items over 26 tasks plus 321 adversarial dialogues; 22 models in the paper
- Public split: Data and scripts on GitHub; the board uses a hard subset
- Grading: Exact match for objective tasks, micro-F1 for extraction, three LLM judges with rubrics for open-ended tasks, and HICS for multi-turn safety.
- Licence: Not stated
- Submission: Through the OpenCompass leaderboard site. The paper does not say how to submit.
- Products allowed: Models only
- Latest version: v4 (arXiv, 2026-02-13)
- What it does not cover: Non-Chinese markets and end-to-end products.
- Last checked: 6 Nov 2026
- Links: paper https://arxiv.org/html/2512.09506v4, code https://github.com/VertiAIBench/CNFinBench, leaderboard https://cnfinbench.opencompass.org.cn
- Directory page: https://benchmarks.finance/benchmarks/cnfinbench/
- Leaderboard: https://benchmarks.finance/leaderboards/cnfinbench/

## Results

No scores recorded here yet.

Source: https://benchmarks.finance/benchmarks/cnfinbench/

Created and maintained by Moneda.