# OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety

arXiv: https://arxiv.org/abs/2403.12316 · HTML: https://mlsanity.com/paper/2403.12316/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [CLUE: A Chinese Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2004.05986/) (2020)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [Evaluating the Performance of Large Language Models on GAOKAO Benchmark](https://mlsanity.com/paper/2305.12474/) (2023)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Optimal Policies Tend to Seek Power](https://mlsanity.com/paper/1912.01683/) (2019)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [Evaluating Language-Model Agents on Realistic Autonomous Tasks](https://mlsanity.com/paper/2312.11671/) (2023)
- [CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?](https://mlsanity.com/paper/2306.16636/) (2023)
- [Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases](https://mlsanity.com/paper/2303.14742/) (2023)
- [Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension](https://mlsanity.com/paper/1904.09679/) (2019)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [ChID: A Large-scale Chinese IDiom Dataset for Cloze Test](https://mlsanity.com/paper/1906.01265/) (2019)
- [Escalation Risks from Language Models in Military and Diplomatic Decision-Making](https://mlsanity.com/paper/2401.03408/) (2024)
- [Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation](https://mlsanity.com/paper/2306.05783/) (2023)

## Built on by (most cited first, 9 of 9)

- [Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning](https://mlsanity.com/paper/2411.14497/) (2024)
- [Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues](https://mlsanity.com/paper/2412.09049/) (2024)
- [What is the best model? Application-driven Evaluation for Large Language Models](https://mlsanity.com/paper/2406.10307/) (2024)
- [CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models](https://mlsanity.com/paper/2406.04752/) (2024)
- [Evaluating LLMs on Chinese Idiom Translation](https://mlsanity.com/paper/2508.10421/) (2025)
- [Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models](https://mlsanity.com/paper/2503.22968/) (2025)
- [DEP: A Decentralized Large Language Model Evaluation Protocol](https://mlsanity.com/paper/2603.01167/) (2026)
- [From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models](https://mlsanity.com/paper/2604.25167/) (2026)
- [SkillAtlas: An Attack Trace Library for Agent Skills](https://mlsanity.com/paper/2609.13353/) (2026)

## Abstract (arXiv)

The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety.