├── assets └── framework.png ├── .gitignore ├── README.md └── LICENSE /assets/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/open-compass/CompassJudger/HEAD/assets/framework.png -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 110 | .pdm.toml 111 | .pdm-python 112 | .pdm-build/ 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards 2 | 3 | 4 |

5 | 6 | OpenCompass GitHub 10 | 11 | 12 | CompassJudger-2 Paper on arXiv 16 | 17 | 18 | CompassJudger-2 Model 22 | 23 | 24 | OpenCompass Discord 28 | 29 |

30 | 31 | > Taolin Zhang*, Maosong Cao*, Alexander Lam, Songyang Zhang, Kai Chen 32 | > 33 | > Recently, the role of LLM-as-judge in evaluating large language models has gained prominence. However, current judge models suffer from narrow specialization and limited robustness, undermining their capacity for comprehensive evaluations. In this work, we present \textit{CompassJudger-2}, a novel generalist judge model that overcomes these limitations via a task-driven, multi-domain data curation strategy. Central to our approach is supervising judgment tasks with verifiable rewards, guiding intrinsic critical reasoning through rejection sampling to foster robust, generalizable judgment capabilities. We introduce a refined learning objective with margin policy gradient loss to enhance performance. Empirically, CompassJudger-2 achieves superior results across multiple judge and reward benchmarks, and our 7B model demonstrates competitive judgment accuracy with significantly larger models like DeepSeek-V3 and Qwen3-235B-A22B. Additionally, we propose JudgerBenchV2, a comprehensive benchmark evaluating cross-domain judgment accuracy and rank consistency to standardize judge model evaluation. These contributions advance robust, scalable LLM judgment and establish new performance and evaluation standards. 34 | 35 |

36 | 37 | ## 📢 News 38 | 39 | - **July 11, 2025:** Our paper, **CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards**, is now available. 40 | 41 | ## 🤗 Models 42 | 43 | | Model Name | Size | Base Model | Download | Notes | 44 | | :--------------------------------- | :--: | :------------------- | :----------------------------------------------------------: | :-------------------------------------------- | 45 | | 👉 **CompassJudger-1-7B-Instruct** | 7B | Qwen2.5-7B-Instruct | 🤗 [Model](https://huggingface.co/opencompass/CompassJudger-1-7B-Instruct) | CompassJudger-1 7B Model. | 46 | | 👉 **CompassJudger-2-32B-Instruct** | 32B | Qwen2.5-32B-Instruct | 🤗 [Model](https://huggingface.co/opencompass/CompassJudger-1-32B-Instruct) | CompassJudger-1 32B Model. | 47 | | 👉 **CompassJudger-2-7B-Instruct** | 7B | Qwen2.5-7B-Instruct | 🤗 [Model](https://huggingface.co/opencompass/CompassJudger-2-7B-Instruct) | Fine-tuned for generalist judge capabilities. | 48 | | 👉 **CompassJudger-2-32B-Instruct** | 32B | Qwen2.5-32B-Instruct | 🤗 [Model](https://huggingface.co/opencompass/CompassJudger-2-32B-Instruct) | A larger, more powerful judge model. | 49 | 50 | ## 🔥 Quick Start 51 | 52 | ```python 53 | import torch 54 | from transformers import AutoModelForCausalLM, AutoTokenizer 55 | 56 | model_path = "opencompass/CompassJudger-2-7B-Instruct" 57 | 58 | model = AutoModelForCausalLM.from_pretrained( 59 | model_name, 60 | torch_dtype="auto", 61 | device_map="auto" 62 | ) 63 | tokenizer = AutoTokenizer.from_pretrained(model_name) 64 | 65 | # Example: Pair-wise Comparison 66 | prompt = """ 67 | Please act as an impartial judge to evaluate the responses provided by two AI assistants to the user question below. Your evaluation should focus on the following criteria: helpfulness, relevance, accuracy, depth, creativity, and level of detail. 68 | 69 | - Do not let the order of presentation, response length, or assistant names influence your judgment. 70 | - Base your decision solely on how well each response addresses the user’s question and adheres to the instructions. 71 | 72 | Your final reply must be structured in the following format: 73 | { 74 | "Choice": "[Model A or Model B]" 75 | } 76 | 77 | User Question: {question} 78 | 79 | Model A's Response: {answerA} 80 | 81 | Model B's Response: {answerB} 82 | 83 | Now it's your turn. Please provide selection result as required: 84 | """ 85 | 86 | messages = [ 87 | {"role": "user", "content": prompt} 88 | ] 89 | 90 | text = tokenizer.apply_chat_template( 91 | messages, 92 | tokenize=False, 93 | add_generation_prompt=True 94 | ) 95 | model_inputs = tokenizer([text], return_tensors="pt").to(model.device) 96 | 97 | generated_ids = model.generate( 98 | **model_inputs, 99 | max_new_tokens=2048 100 | ) 101 | generated_ids = [ 102 | output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) 103 | ] 104 | 105 | response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] 106 | print(response) 107 | ``` 108 | 109 | ## 📊 JudgerBenchV2 110 | 111 | ### Evaluate on JudgerBenchV2 112 | We provide scripts for evaluating JudgerBenchV2 within the OpenCompass framework. Please refer to the [OpenCompass](https://github.com/open-compass/opencompass) repository. 113 | 114 | Modify the `models` in `examples/eval_judgerbenchv2.py` to your judge model, then run: 115 | ```bash 116 | git clone https://github.com/open-compass/opencompass opencompass 117 | cd opencompass 118 | pip install -e . 119 | python run.py examples/eval_judgerbenchv2.py --mode all --reuse latest 120 | ``` 121 | 122 | ## 📊 Benchmarks 123 | 124 | ### Judge Model Benchmarks. 125 | CompassJudger-2 achieves state-of-the-art performance on major judge benchmarks across both 7B and 32B+ variants. 126 | 127 | | Model | JudgerBenchV2 | JudgeBench | RMB | RewardBench | Average | 128 | | :------------------------------- | :-----------: | :--------: | :-------: | :---------: | :-------: | 129 | | **General Models** | | | | | | 130 | | Qwen2.5-7B-Instruct | 57.14 | 23.23 | 69.03 | 79.69 | 57.27 | 131 | | Llama3.1-8B-Instruct | 57.64 | 33.23 | 66.01 | 73.64 | 57.63 | 132 | | Qwen2.5-32B-Instruct | 62.97 | 59.84 | 74.99 | 85.61 | 70.85 | 133 | | DeepSeek-V3-0324 | 64.43 | 59.68 | 78.16 | 85.17 | 71.86 | 134 | | Qwen3-235B-A22B | 61.40 | 65.97 | 75.59 | 84.68 | 71.91 | 135 | | **7B Judge Models** | | | | | | 136 | | CompassJudger-1-7B-Instruct | 57.96 | 46.00 | 38.18 | 80.74 | 55.72 | 137 | | Con-J-7B-Instruct | 52.35 | 38.06 | 71.50 | 87.10 | 62.25 | 138 | | RISE-Judge-Qwen2.5-7B | 46.12 | 40.48 | 72.64 | 88.20 | 61.61 | 139 | | **CompassJudger-2-7B-Instruct** | **60.52** | **63.06** | **73.90** | **90.96** | **72.11** | 140 | | **32B+ Judge Models** | | | | | | 141 | | CompassJudger-1-32B-Instruct | 60.33 | 62.29 | 77.63 | 86.17 | 71.61 | 142 | | RISE-Judge-Qwen2.5-32B | 56.42 | 63.87 | 73.70 | 92.70 | 71.67 | 143 | | **CompassJudger-2-32B-Instruct** | **62.21** | **65.48** | **72.98** | **92.62** | **73.32** | 144 | 145 | 146 | ## ✍️ Citation 147 | 148 | ```bibtex 149 | @article{zhang2025compassjudger, 150 | title={CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards}, 151 | author={Zhang, Taolin and Cao, Maosong and Lam, Alexander and Zhang, Songyang and Chen, Kai}, 152 | journal={arXiv preprint arXiv:2507.09104}, 153 | year={2025} 154 | } 155 | @article{cao2024compass, 156 | title={CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution}, 157 | author={Maosong Cao, Alexander Lam, Haodong Duan, Hongwei Liu, Songyang Zhang, Kai Chen}, 158 | journal={arXiv preprint arXiv:2410.16256}, 159 | year={2024} 160 | } 161 | ``` 162 | 163 | 164 | ## 📜 License 165 | CompassJudger-2 is licensed under the Apache 2.0. -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | https://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | --------------------------------------------------------------------------------