👋 join us on Twitter, Discord and WeChat
to OpenCompass!
Just like a compass guides us on our journey, OpenCompass will guide you through the complex landscape of evaluating large language models. With its powerful algorithms and intuitive interface, OpenCompass makes it easy to assess the quality and effectiveness of your NLP models.
- [2023.08.11] Model comparison is now online. We hope this feature offers deeper insights! 🔥🔥🔥.
- [2023.08.11] We have supported LEval. 🔥🔥🔥.
- [2023.08.10] OpenCompass is compatible with LMDeploy. Now you can follow this instruction to evaluate the accelerated models provide by the Turbomind.
- [2023.08.10] We have supported Qwen-7B and XVERSE-13B ! Go to our leaderboard for more results! More models are welcome to join OpenCompass.
- [2023.08.09] Several new datasets(CMMLU, TydiQA, SQuAD2.0, DROP) are updated on our leaderboard! More datasets are welcomed to join OpenCompass.
- [2023.08.07] We have added a script for users to evaluate the inference results of MMBench-dev.
- [2023.08.05] We have supported GPT-4! Go to our leaderboard for more results! More models are welcome to join OpenCompass.
- [2023.07.27] We have supported CMMLU! More datasets are welcome to join OpenCompass.
- [2023.07.21] Performances of Llama-2 are available in OpenCompass leaderboard!
- [2023.07.13] We release MMBench, a meticulously curated dataset to comprehensively evaluate different abilities of multimodality models.
OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features includes:
-
Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 50+ datasets with about 300,000 questions, comprehensively evaluating the capabilities of the models in five dimensions.
-
Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours.
-
Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue type prompt templates, to easily stimulate the maximum performance of various models.
-
Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded!
-
Experiment management and reporting mechanism: Use config files to fully record each experiment, support real-time reporting of results.
We provide OpenCompass Leaderbaord for community to rank all public models and API models. If you would like to join the evaluation, please provide the model repository URL or a standard API interface to the email address opencompass@pjlab.org.cn.
| Language | Knowledge | Reasoning | Comprehensive Examination | Understanding |
Word Definition
Idiom Learning
Semantic Similarity
Coreference Resolution
Translation
|
Knowledge Question Answering
Multi-language Question Answering
|
Textual Entailment
Commonsense Reasoning
Mathematical Reasoning
Theorem Application
Code
Comprehensive Reasoning
|
Junior High, High School, University, Professional Examinations
|
Reading Comprehension
Content Summary
Content Analysis
|
| Open-source Models | API Models |
|
|
Below are the steps for quick installation and datasets preparation.
conda create --name opencompass python=3.10 pytorch torchvision pytorch-cuda -c nvidia -c pytorch -y
conda activate opencompass
git clone https://github.com/InternLM/opencompass opencompass
cd opencompass
pip install -e .
# Download dataset to data/ folder
wget https://github.com/InternLM/opencompass/releases/download/0.1.1/OpenCompassData.zip
unzip OpenCompassData.zipSome third-party features, like Humaneval and Llama, may require additional steps to work properly, for detailed steps please refer to the Installation Guide.
Make sure you have installed OpenCompass correctly and prepared your datasets according to the above steps. Please read the Quick Start to learn how to run an evaluation task.
For more tutorials, please check our Documentation.
We appreciate all contributions to improve OpenCompass. Please refer to the contributing guideline for the best practice.
Some code in this project is cited and modified from OpenICL.
Some datasets and prompt implementations are modified from chain-of-thought-hub and instruct-eval.
@misc{2023opencompass,
title={OpenCompass: A Universal Evaluation Platform for Foundation Models},
author={OpenCompass Contributors},
howpublished = {\url{https://github.com/InternLM/OpenCompass}},
year={2023}
}