evalscope 0.12.0__py3-none-any.whl → 0.13.0__py3-none-any.whl

evalscope/utils/logger.py

@@ -12,12 +12,12 @@ detailed_formatter = logging.Formatter(detailed_format)
 simple_formatter = logging.Formatter(simple_format)
 DEFAULT_LEVEL = logging.DEBUG if os.getenv('LOG_LEVEL', 'INFO') == 'DEBUG' else logging.INFO
 
-logging.basicConfig(format=simple_format, level=DEFAULT_LEVEL)
+logging.basicConfig(format=simple_format, level=DEFAULT_LEVEL, force=True)
 
-# disable datasets logging
+# set logging level
 logging.getLogger('datasets').setLevel(logging.WARNING)
-logging.getLogger('modelscope').setLevel(logging.WARNING)
 logging.getLogger('httpx').setLevel(logging.WARNING)
+logging.getLogger('modelscope').setLevel(logging.ERROR)
 
 
 def get_logger(log_file: Optional[str] = None, log_level: int = DEFAULT_LEVEL, file_mode: str = 'w', force=False):

evalscope/version.py

@@ -1,4 +1,4 @@
 # Copyright (c) Alibaba, Inc. and its affiliates.
 
-__version__ = '0.12.0'
-__release_datetime__ = '2025-02-27 21:00:00'
+__version__ = '0.13.0'
+__release_datetime__ = '2025-03-14 12:00:00'

{evalscope-0.12.0.dist-info → evalscope-0.13.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.12.0
+Version: 0.13.0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -175,16 +175,29 @@ Requires-Dist: ms-vlmeval>=0.0.9; extra == "vlmeval"
 > ⭐ If you like this project, please click the "Star" button at the top right to support us. Your support is our motivation to keep going!
 
 ## 📋 Contents
-- [Introduction](#-introduction)
-- [News](#-news)
-- [Installation](#️-installation)
-- [Quick Start](#-quick-start)
+- [📋 Contents](#-contents)
+- [📝 Introduction](#-introduction)
+- [☎ User Groups](#-user-groups)
+- [🎉 News](#-news)
+- [🛠️ Installation](#️-installation)
+  - [Method 1: Install Using pip](#method-1-install-using-pip)
+  - [Method 2: Install from Source](#method-2-install-from-source)
+- [🚀 Quick Start](#-quick-start)
+  - [Method 1. Using Command Line](#method-1-using-command-line)
+  - [Method 2. Using Python Code](#method-2-using-python-code)
+  - [Basic Parameter](#basic-parameter)
+  - [Output Results](#output-results)
+- [📈 Visualization of Evaluation Results](#-visualization-of-evaluation-results)
+- [🌐 Evaluation of Specified Model API](#-evaluation-of-specified-model-api)
+- [⚙️ Custom Parameter Evaluation](#️-custom-parameter-evaluation)
+  - [Parameter](#parameter)
 - [Evaluation Backend](#evaluation-backend)
-- [Custom Dataset Evaluation](#️-custom-dataset-evaluation)
-- [Model Serving Performance Evaluation](#-model-serving-performance-evaluation)
-- [Arena Mode](#-arena-mode)
-- [Contribution](#️-contribution)
-- [Roadmap](#-roadmap)
+- [📈 Model Serving Performance Evaluation](#-model-serving-performance-evaluation)
+- [🖊️ Custom Dataset Evaluation](#️-custom-dataset-evaluation)
+- [🏟️ Arena Mode](#️-arena-mode)
+- [👷‍♂️ Contribution](#️-contribution)
+- [🔜 Roadmap](#-roadmap)
+- [Star History](#star-history)
 
 
 ## 📝 Introduction
@@ -225,10 +238,16 @@ Please scan the QR code below to join our community groups:
 
 
 ## 🎉 News
-- 🔥 **[2025.02.27]** Added support for evaluating the reasoning efficiency of models. Refer to [📖 Best Practices for Evaluating Thinking Efficiency](https://evalscope.readthedocs.io/zh-cn/latest/best_practice/think_eval.html). This implementation is inspired by the works [Overthinking](https://doi.org/10.48550/arXiv.2412.21187) and [Underthinking](https://doi.org/10.48550/arXiv.2501.18585).
+
+- 🔥 **[2025.03.13]** Added support for the [LiveCodeBench](https://www.modelscope.cn/datasets/AI-ModelScope/code_generation_lite/summary) code evaluation benchmark. You can use it by specifying `live_code_bench`.
+- 🔥 **[2025.03.11]** Added support for the [SimpleQA](https://modelscope.cn/datasets/AI-ModelScope/SimpleQA/summary) and [Chinese SimpleQA](https://modelscope.cn/datasets/AI-ModelScope/Chinese-SimpleQA/summary) evaluation benchmarks. These are used to assess the factual accuracy of models, and you can specify `simple_qa` and `chinese_simpleqa` for use. Support for specifying a judge model is also available. For more details, refer to the [relevant parameter documentation](https://evalscope.readthedocs.io/en/latest/get_started/parameters.html).
+- 🔥 **[2025.03.07]** Added support for the [QwQ-32B](https://modelscope.cn/models/Qwen/QwQ-32B/summary) model, evaluate the model's reasoning ability and reasoning efficiency, refer to [📖 Best Practices for QwQ-32B Evaluation](https://evalscope.readthedocs.io/en/latest/best_practice/eval_qwq.html) for more details.
+- 🔥 **[2025.03.04]** Added support for the [SuperGPQA](https://modelscope.cn/datasets/m-a-p/SuperGPQA/summary) dataset, which covers 13 categories, 72 first-level disciplines, and 285 second-level disciplines, totaling 26,529 questions. You can use it by specifying `super_gpqa`.
+- 🔥 **[2025.03.03]** Added support for evaluating the IQ and EQ of models. Refer to [📖 Best Practices for IQ and EQ Evaluation](https://evalscope.readthedocs.io/en/latest/best_practice/iquiz.html) to find out how smart your AI is!
+- 🔥 **[2025.02.27]** Added support for evaluating the reasoning efficiency of models. Refer to [📖 Best Practices for Evaluating Thinking Efficiency](https://evalscope.readthedocs.io/en/latest/best_practice/think_eval.html). This implementation is inspired by the works [Overthinking](https://doi.org/10.48550/arXiv.2412.21187) and [Underthinking](https://doi.org/10.48550/arXiv.2501.18585).
 - 🔥 **[2025.02.25]** Added support for two model inference-related evaluation benchmarks: [MuSR](https://modelscope.cn/datasets/AI-ModelScope/MuSR) and [ProcessBench](https://www.modelscope.cn/datasets/Qwen/ProcessBench/summary). To use them, simply specify `musr` and `process_bench` respectively in the datasets parameter.
 - 🔥 **[2025.02.18]** Supports the AIME25 dataset, which contains 15 questions (Grok3 scored 93 on this dataset).
-- 🔥 **[2025.02.13]** Added support for evaluating DeepSeek distilled models, including AIME24, MATH-500, and GPQA-Diamond datasets，refer to [best practice](https://evalscope.readthedocs.io/zh-cn/latest/best_practice/deepseek_r1_distill.html); Added support for specifying the `eval_batch_size` parameter to accelerate model evaluation.
+- 🔥 **[2025.02.13]** Added support for evaluating DeepSeek distilled models, including AIME24, MATH-500, and GPQA-Diamond datasets，refer to [best practice](https://evalscope.readthedocs.io/en/latest/best_practice/deepseek_r1_distill.html); Added support for specifying the `eval_batch_size` parameter to accelerate model evaluation.
 - 🔥 **[2025.01.20]** Support for visualizing evaluation results, including single model evaluation results and multi-model comparison, refer to the [📖 Visualizing Evaluation Results](https://evalscope.readthedocs.io/en/latest/get_started/visualization.html) for more details; Added [`iquiz`](https://modelscope.cn/datasets/AI-ModelScope/IQuiz/summary) evaluation example, evaluating the IQ and EQ of the model.
 - 🔥 **[2025.01.07]** Native backend: Support for model API evaluation is now available. Refer to the [📖 Model API Evaluation Guide](https://evalscope.readthedocs.io/en/latest/get_started/basic_usage.html#api) for more details. Additionally, support for the `ifeval` evaluation benchmark has been added.
 - 🔥🔥 **[2024.12.31]** Support for adding benchmark evaluations, refer to the [📖 Benchmark Evaluation Addition Guide](https://evalscope.readthedocs.io/en/latest/advanced_guides/add_benchmark.html); support for custom mixed dataset evaluations, allowing for more comprehensive model evaluations with less data, refer to the [📖 Mixed Dataset Evaluation Guide](https://evalscope.readthedocs.io/en/latest/advanced_guides/collection/index.html).

{evalscope-0.12.0.dist-info → evalscope-0.13.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=lYxhmZVs-dUz8q9cpwjoe-HuwglkkgxiSaluuXlAmAc,4814
-evalscope/config.py,sha256=BZv7maQTbxXkb2WzdeGGQr0U01_TXy-Q7PujOiPJ4D8,8703
-evalscope/constants.py,sha256=bkcDVbB4Pr1Qxz83qefcWjEetVGiHTcx3m84WX14ASI,3330
-evalscope/run.py,sha256=zRdBJEYdQ6JzH94eA7gfkzFAvsn3UFwdrvX_snaqGNU,5702
+evalscope/arguments.py,sha256=VhZd7a8PoZK01qFCMEADLINqLYi6njRqRb50iR1l1lo,5241
+evalscope/config.py,sha256=9bMV7wf8pM7N5dEj_kJsCq6oM8xobzQDYh0NF8h-j1I,9313
+evalscope/constants.py,sha256=ydS8oihksGnvvzvJZw7HGhEeeccHNpJxspB81gAv29Y,3720
+evalscope/run.py,sha256=Udz-H503UaMYos0ic3A_npXIbnd4eJLx26q5UEahF-U,5797
 evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
 evalscope/summarizer.py,sha256=Wnt8Y61PasOkigo8zMpi1qdFzfETjfnDtCDDQ6VwgDw,5867
-evalscope/version.py,sha256=RDE_Gbn1y54qtXxjxbZOTLDFSkq__2Zy3rAOwyVrvPs,119
+evalscope/version.py,sha256=a1r1BkZoSpoA_eGXZoXm6WaLayRHhF__TgvE9xG-Whs,119
 evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/backend/base.py,sha256=qYu8Shokrtrx-N6T_BAJk_6OCpovUBYuN0p3wngt-dw,1030
 evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
@@ -56,16 +56,17 @@ evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4ty
 evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=ZB0wYzPBPyIM0zjfp5C71GcjAgKxKoWxF7RrhuDQBYM,5931
 evalscope/backend/vlm_eval_kit/custom_dataset.py,sha256=D-8Sr0tZblf-3ZR5T0lOggbgFRuy5wq9Nm02GUpNyAs,1620
 evalscope/benchmarks/__init__.py,sha256=b_SWdV1ZyOqFiwc_9lIjKrIvK1rwnF2cCIF7XN9CN8E,932
-evalscope/benchmarks/benchmark.py,sha256=Kaes5Bg9_bvFO99-JztNlv_TPg4jH9vMYvnMcb1C_G8,2507
-evalscope/benchmarks/data_adapter.py,sha256=e4mtvzlC8ehQ0N4C5PAGJFv5N9Y42WT-OklwaV-Ex1Y,15239
+evalscope/benchmarks/benchmark.py,sha256=a_7Ctz36McuTyBSTYi56jis9pvOdWhg7JVSPFrbxqR4,2535
+evalscope/benchmarks/data_adapter.py,sha256=2u9oC4RBHVfEMHKPRu87xM4XOw_RS2Z2fvagNsciEo4,16791
+evalscope/benchmarks/utils.py,sha256=6kxeBz4w8Fw68AYH05a4ncjgkaUV4bU3eaFVLqOdkMI,1321
 evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/aime/aime24_adapter.py,sha256=FYH8NsT1nis3VoBMzRM_ueOsGNXjOKZCa6J_wpUM3RQ,1772
-evalscope/benchmarks/aime/aime25_adapter.py,sha256=bws4dajr5xuMDvuTluDb80oBYUTUlu_geKvmnNO3_OQ,1766
+evalscope/benchmarks/aime/aime24_adapter.py,sha256=dBm9yukt4-CByEPUlAPAIN6mL3VkZcI-dw2kz4oQBMo,1715
+evalscope/benchmarks/aime/aime25_adapter.py,sha256=FB_NufY2V7uYdxVnrY_4y81gyyfYDnvedz1_zHdDWt4,1709
 evalscope/benchmarks/arc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/arc/ai2_arc.py,sha256=WtL4Z_ulcCU2KfptWTjTm75T2I2rVGd9aDBBB76P14w,5697
-evalscope/benchmarks/arc/arc_adapter.py,sha256=vfwAy01LA141qn1lsSyZmEIGWbbhOCRMOGoSM-K2z6M,6490
+evalscope/benchmarks/arc/arc_adapter.py,sha256=lkhDz-DYjPQ1vHzo8X4j-0Lq_rBxAnws35_R00pIbNI,6347
 evalscope/benchmarks/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/bbh/bbh_adapter.py,sha256=cep-Ws9Tozju6JWls1-oz3lKYqTL8q8Cee_d-d3cLIo,8407
+evalscope/benchmarks/bbh/bbh_adapter.py,sha256=fROpzenrjpEBWtnvM_RL_m0uXPOhXTtYAglJEZbzUdY,8330
 evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt,sha256=xnzlaIRyeGlogG49v8nt4vpJO40J06ev4yc8cv0VSRY,1781
 evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt,sha256=sfo-2iOeVzB0OGgd7NSQFELTGDTsr2DQ3u-g0ivI-sM,3653
 evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt,sha256=UJBsc3Mwz8TZngdWH_NFlhhNbLhNHK6FvW9FHcS8H5g,1167
@@ -94,65 +95,83 @@ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt
 evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt,sha256=s_x6u5MLeKpuAHZj3GNQqY1I8vWqQIfJasOp9XcM7Ck,2945
 evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt,sha256=qfTZafCzNiz9ULBaDlfy_LISL617NyH5Nc0-nO0K0LE,2164
 evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/ceval/ceval_adapter.py,sha256=Qz2oNGw0H_4FtfY-Izdxv9fgwxScJksyvwzeQw-aVyo,11374
+evalscope/benchmarks/ceval/ceval_adapter.py,sha256=E4QobCjSSkMZtPJyaT_XBVxiqEqa1bta1I9aFnaHOqs,11308
 evalscope/benchmarks/ceval/ceval_exam.py,sha256=ngOvb6Fymt7iPWIb2fzrUVpqmUT2VBoqh7X_IH8Bcsc,4824
+evalscope/benchmarks/chinese_simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=nKF_a0yc_PbZYjYA_-gJh3ePZIEz5txrhDV4IsTqD4Q,8196
 evalscope/benchmarks/cmmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/cmmlu/cmmlu.py,sha256=Y59NIGUFzJEztJbkehZsG4Cz0J_v9Cyju6xazHMYIcA,5022
-evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=1RmhI0SNxHK-Fz-iTIR76zeBRDLlm0m6_7rJywqk3Rk,10446
+evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=TTq2jRz46Hqc_D_ZBaiw_OwKub1FZX6w8C7g7COIdGs,10372
 evalscope/benchmarks/cmmlu/samples.jsonl,sha256=FXbyPQSDorKBGSD0lnOzioZmFjG07lIL87FRDRaMPSY,1722
 evalscope/benchmarks/competition_math/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/competition_math/competition_math.py,sha256=Cehyokift7oDKjc8TdmfblZ6mMc39wQWtqqbUi34QLc,2629
-evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=_vGkfgP5ZnQh3AlbJqycQOL_gQHayazMYFzHVo2e5O8,6902
+evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=F2YCaNDn49X82l06WlLFp2OPFB7nv0ecW40099I9iSE,6871
 evalscope/benchmarks/data_collection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=o3Q6ke-RLx4qUbF5FgASZogv3-kCJ6qpK43F_LARU3Y,2496
+evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=U4M-0MVJS3-z03YW8nafooFJ7x60e5uEpBO5z_c7zk8,2450
 evalscope/benchmarks/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=M-PocYW4pkGtKOKvFZW-bIoztcGvmHn5Gf5o7F71xCg,5248
+evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=ZVGzUuuQ0UTOqQtXE40ZyBeMOSl8saSiFEQ5_siJ-c8,5052
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=_t2ZNsQzY5AuOOBXkEVNGIB3pZgLKQmw7-5gEqR_Z_k,3848
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=ELDdS5T3JZeSWVv1ldawcHzLwAljEWKqakbRMVcBvgw,4741
 evalscope/benchmarks/gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/gpqa/chain_of_thought.txt,sha256=pgoT5a-DMPJaMhoH_M8zfU5s80ibWDTVW6vnonITd8k,5610
-evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=1zI6GWfvPiKaZg39N7pSFw2R-GpbrjEo-11K_waq6Dg,4686
+evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=UB287DtnbkSQXZsbReFJqmQRwbo672DTCeXXilR_-Vc,4790
 evalscope/benchmarks/gsm8k/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/gsm8k/gsm8k.py,sha256=ZDN5lfeZyc_pkTDVY0voC_zUExHE1ZoEgEaTvt5hpXg,4233
-evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=X7fu2mx911Al-7a6j-mJQ3vqTb0cN0u7FoJTrNf6AN4,10661
+evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=ZZZ-9oja53IwiU33Kjm7NTk4MbFGWyvonhnHrn_3Na8,10557
 evalscope/benchmarks/hellaswag/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/hellaswag/hellaswag.py,sha256=5_c9WbaS1LIdvgXzqEcvjAEtKi2V2Yn0YtszPlFqhXI,4610
-evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=qArX2umdrYJZkDA9i3XGBGljCton99v5Yss9be9iZYw,6269
+evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=QYZZuxbjkKxAjxuoWn0M5WgusO55vzeAcyKnWUMow3M,5871
 evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/humaneval/humaneval.py,sha256=2Exsg6u8FEu0buADY2tETJluSM8tWacvX06nykKKLSE,3395
-evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=onacZB_6SF9239Ly-U70__WYsinS9iWpnf3oiYMNxKc,5164
+evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=UOjakV31J0g7TYbrRls0ItcopWOJu54ucPfaqSJB7Os,5250
 evalscope/benchmarks/ifeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=zmN69NDhBR3NJak1cB0z3DqPMuoAvqADWMapQPnvGLs,2025
+evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=R7MILWuMglvXr7yWioBxyJ2T4EdEkwRZ1lnvWqZqG28,1922
 evalscope/benchmarks/ifeval/instructions.py,sha256=oaJ9D_4rvS67BraHBNPpDtFd4TblFAnR4A3YW9HWfuY,56304
 evalscope/benchmarks/ifeval/instructions_registry.py,sha256=tVUmhuSwnOidLtI8onOAw_gpJ6bi8FL07GiX19hSuo8,7288
 evalscope/benchmarks/ifeval/instructions_util.py,sha256=vkemXeylJMmgW8LgfQe4cSy2OF-oH_NcSZtzyZDURW4,25780
 evalscope/benchmarks/ifeval/utils.py,sha256=TKrM1m2qDCUauahogItDdICf4mDk0OjasSxgnxjt2KY,4517
 evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=nv4mzKOPp1YPcr6e7daZuZyQ3jRNNG6PUzi38REuwSk,2356
+evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=16whmFkJt9fLbei9d-kmjnWB_5y5vsiX9tK5kSuxDw8,2449
+evalscope/benchmarks/live_code_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/live_code_bench/evaluate_utils.py,sha256=rOWaG8PV4AGIRhS_gqwxEhphEVe1Cqg57Eudwm5HTjI,6820
+evalscope/benchmarks/live_code_bench/execute_utils.py,sha256=MreaMLI0IicNZawpfqcyoRLt67EZ3CJvmxxRTYwhAbU,7397
+evalscope/benchmarks/live_code_bench/extract_utils.py,sha256=ZcQ8y741uawPo6I_1_XglR3eqJFDNrqc8fILKZupVRs,2375
+evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py,sha256=8MOECcweLG465JFgUzP20QlKyBAO90oFHhH7Z77FuUY,3521
+evalscope/benchmarks/live_code_bench/load_utils.py,sha256=5i9wtdPLYR8ckjx5MaYQVC2LFYvjKzR6Fa6UZmeOTRc,2445
+evalscope/benchmarks/live_code_bench/pass_k_utils.py,sha256=Ktrp_lXdfFzoHtQNQNdGfIl26ySjaPCHm4Zv-dFvRqM,2024
+evalscope/benchmarks/live_code_bench/prompts.py,sha256=P4KILIAIDT1MKDck0xHYV_6v9820wDZRhxVMazmlL-g,12600
+evalscope/benchmarks/live_code_bench/testing_util.py,sha256=EBe0XzY3B4cW5dCjwLksW7o4R1chZwsuFjxkfqVPFI4,28238
 evalscope/benchmarks/math_500/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/math_500/math_500_adapter.py,sha256=OO3Jx1WuyEMfd4R5znG9_O5ln_SbVVGB5u1bTjiuWaU,2104
+evalscope/benchmarks/math_500/math_500_adapter.py,sha256=SB2eb4Z7DTXdptqirEoctqTdDLEu28s7bLeCAMBmAFo,1923
 evalscope/benchmarks/mmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/mmlu/mmlu.py,sha256=sA8AC0bN7iURrSazqkY31s_reNVbDZSUCB-NCTQsVeI,5042
-evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=pmT1y9dbWJcZK3U6hkXa3-lBDABx7DhQ7oHc3O-Nkg0,11769
+evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=e__Evar99V9l65FlzT6T594CN4iMgmuVhjujQAm4po4,11662
 evalscope/benchmarks/mmlu/samples.jsonl,sha256=f5Y2vwbEvNtpE7vrl9BHoJzsdceI4vUAo1frexYyX2o,1345
 evalscope/benchmarks/mmlu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=73TLdWlEAulZNA0ZMLDQnaXs435vG-gD89yjURjsjpo,4111
+evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=OANfue-fK543drJrDj6V_zDMtySrQEBHPgTsejr-e7U,4226
 evalscope/benchmarks/musr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/musr/musr_adapter.py,sha256=D-CZMTr9Ld_tJxZdCDPZQxDX86BgJqKWCyy5-tlcONY,2343
+evalscope/benchmarks/musr/musr_adapter.py,sha256=Po8hcIQiqlFo0AGjcNQe75cpsMNDcfiJaKgZsk33-DY,2442
 evalscope/benchmarks/process_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/process_bench/critique_template.txt,sha256=tycx8n42QEC0uGcwbIvHfZvfTnchlRxGz8Tp1R2_e_Y,489
-evalscope/benchmarks/process_bench/process_bench_adapter.py,sha256=YavcEDpnURVV0gCWTXDKq81CyEOgn8ASaVQu2h765to,3389
+evalscope/benchmarks/process_bench/process_bench_adapter.py,sha256=ydU-r1T0DaYhOxkhZgGL7PhDd4XoeqOBzVO9oiFPd8M,3422
 evalscope/benchmarks/race/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO61nU,3608
-evalscope/benchmarks/race/race_adapter.py,sha256=dC9I-3T9UFh2OVpmWKRmSszPOlFZAZ40xOPa4zN3daI,6661
+evalscope/benchmarks/race/race_adapter.py,sha256=RD0B-i5dzeNKuhqnWbremgf4tk9jmOO4_eLAiITB1F0,6381
 evalscope/benchmarks/race/samples.jsonl,sha256=bhSktBgU6axYQCClRtQ7nN8D1x815AU8xMAIG1oflG0,1243
+evalscope/benchmarks/simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=SrK18xDe4HyUaIPRLVEDtoF4Nc_ms4aFxktEsj8MnnA,9071
+evalscope/benchmarks/super_gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/super_gpqa/five_shot_prompt.txt,sha256=vD3RMeQustxY_oWA8IobntjywT8ZUO7Jaub--rElDT4,4718
+evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py,sha256=BqNLL8BYnK6tRuIdV6ijL4Uym2SejH_h1BV06XNjSE4,9331
+evalscope/benchmarks/super_gpqa/utils.py,sha256=ftYPP9ODvLBlQSd9ltACx9iRIvjB8u1bg4AtgcJ4JAI,3360
+evalscope/benchmarks/super_gpqa/zero_shot_prompt.txt,sha256=y7hR9SmoR_YqoEWtT8N9JpZOpeJIlg0cDGDgYw6R6hM,237
 evalscope/benchmarks/trivia_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/trivia_qa/samples.jsonl,sha256=1isBD62PGhCiNbzQa-GFrHHL4XLHIkojWfgSvn7ktf8,3445
 evalscope/benchmarks/trivia_qa/trivia_qa.py,sha256=eekxaXppMLb5tCQqNLOw2MaWlYDhI2IicPzRsTHqb5A,3070
-evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=GVuJT-Xz4ugVtcUSTRxcBgViHVowcqJf3yVsotcZoZI,5062
+evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=7tMc8vVZdBnks5jWrBSrb5BSyjO2eD4On6gX8xqlkV8,4961
 evalscope/benchmarks/truthful_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/truthful_qa/truthful_qa.py,sha256=A4abSL6WMRcXez8flxsHy-0ZFyRg-moq9rTeOA1TalY,6909
-evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=MYMLpIEv3oqRiOgAydqM0ZlzpvbzpCymOKUbca98yxo,12915
+evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=ueUU860kg5_xf_MtUCa6ck-fGHX3ttw8Xh3mWSJyOZA,12617
 evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
 evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
@@ -161,40 +180,42 @@ evalscope/cli/start_eval.py,sha256=MXhVDeaMFd6ny88-gnVtQflH660UaDj240YGYnHccx8,7
 evalscope/cli/start_perf.py,sha256=5hLi5jWgM9BJPXLd8d9D1zqrcj_5c0KvkfB1DgD4_RU,831
 evalscope/cli/start_server.py,sha256=DQRIfbsHaOAsVcLGF6iRyJnxmd5Sf_tgytpJNfiWCeE,3662
 evalscope/collections/__init__.py,sha256=hd68Qf-ryeDsz5Pu-Dh83M5V5RE5mhLsG-vc55n5n0o,228
-evalscope/collections/evaluator.py,sha256=1bz2jEgOlv7qHeCgkFCtd1MPWhMa6XnZfP4XJBhTnUc,12321
+evalscope/collections/evaluator.py,sha256=okP4_a5vuM-Z0O_4ntauuyn2NeH228JUo_YrbrTqKPM,12741
 evalscope/collections/sampler.py,sha256=2NwvhJVdi-mrDeK7RWwEGOoE7DdxtpyASRUZU_D6hWw,4855
 evalscope/collections/schema.py,sha256=mjJfNmy_athJ1TmnuJRkrKRlefzefuQXZuTtjn8SHKo,4073
 evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
-evalscope/evaluator/evaluator.py,sha256=VIiw1eI46UOsFWNd7schD4ah_Q5ll0crl2sRmGIRmig,17649
+evalscope/evaluator/evaluator.py,sha256=yj7ds5WMYqQcRw3B3x11-cajl4DmWsLM_3kO1n2k7OE,19734
 evalscope/evaluator/rating_eval.py,sha256=uo0uj9z_TDsxdYlT8WIfNZhFLAfRkW9zn_wlu-F72O0,5575
 evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/evaluator/reviewer/auto_reviewer.py,sha256=PDz1Nt_qq0oGZBBwek2-M8VBUNLkOkmYObzR8gO7nEc,16624
 evalscope/metrics/__init__.py,sha256=SWvqzUzdryW5URz6u4fPkP9XSyA09nQ8zBeE8BbchSg,349
 evalscope/metrics/code_metric.py,sha256=EXE2BZAc9JJT_cpd6eCb0Jo9wwtnzXzHBZxmLzG5Jpw,3300
+evalscope/metrics/llm_judge.py,sha256=g9pLMJPNTUyw0sGteblws1_e_KzbRqcbqKcaIzfE_DE,4031
 evalscope/metrics/math_parser.py,sha256=uTDudn305G3b8-GboWTrDE6OfrEwAW-areHnoGXZ6Is,17302
 evalscope/metrics/metrics.py,sha256=_YI7RhxlFu_JOgeE3LF9UKu6mJruvyu4FgqVf78Bjb8,13813
-evalscope/metrics/named_metrics.py,sha256=SeBXmgWyK4y4tKiGKro3k-CZU1OShuKe6qxwpT3tizY,1313
+evalscope/metrics/named_metrics.py,sha256=pSHA2_qdi9B5bDHIh08GYhx63odilSwA_T-95K1Usl0,1380
 evalscope/metrics/rouge_metric.py,sha256=zhIUqenSuxnORR9tamLQBGjFwP91Zei2UiLtcOyseVM,4639
 evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
 evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=Kq6AObenmLVQ5tN3NgN042a6mgRFQmRO21-ohd9mSa8,11972
 evalscope/metrics/resources/gpt2-zhcn3-v4.bpe,sha256=J_K-oSt9usFEw87Av6j7ETn3J48EsmFuY5_iVvY6xjc,524464
 evalscope/metrics/resources/gpt2-zhcn3-v4.json,sha256=WkM4J_FDPPNQwYi0kj5sM5SVjk2_6bci7tqf8dV9p_U,1289341
-evalscope/models/__init__.py,sha256=pafIEbJq_2DrYjQbgI0SNVxywNYOxvqwk7Dr1P7KEwk,923
-evalscope/models/base_adapter.py,sha256=04VK4A5L0naOllBW9fw03GduvBUNgStliyFBTZKY0xU,2297
-evalscope/models/chat_adapter.py,sha256=eji2HCTjRed7K4JRHAmLLwyliPBsEgYbUUY0lJ5-OAY,6126
-evalscope/models/choice_adapter.py,sha256=jj_6KB1BAsvv4Yufn2bM2tCiLovFUum2368lseogmb8,8036
-evalscope/models/custom_adapter.py,sha256=Ed_MGEcZxKK4mkXTpUY4GXTsayprHzIEOC1L9gqwjf4,2284
+evalscope/models/__init__.py,sha256=i9vcOBMEF_UM7C2gpmh2GsQk3njwqevoQ6A4CnP1fHs,1000
+evalscope/models/base_adapter.py,sha256=7PbRwfD5PIZCBYVds6ZHI8TBY9C5i2LdPOTu88FJWlY,3414
+evalscope/models/chat_adapter.py,sha256=5-yz7L41OdeBO9J_qRkEZcduATrYIMe__UFfh7BzjIc,6277
+evalscope/models/choice_adapter.py,sha256=fnJdo-FMJ-zvNLbEJGc73odgWXIxtVudL00JIf2vzsA,8239
+evalscope/models/custom_adapter.py,sha256=Za52WF1I_YcJkGomJ6s9sP2Fs8DoJ4HHBYBi3iC3WNI,2379
 evalscope/models/local_model.py,sha256=yydggBCLcBAmUWbBhv7o2CA3RbG0DwDZharPdrkbNcg,2628
 evalscope/models/model.py,sha256=diu4TE1ZFWdynTxsl4DejTNsLdwjxoyj2nsKR-Y8EZE,7343
-evalscope/models/server_adapter.py,sha256=l_EI1jTaH1EBATKaH1USAdiYkezz7IYUQTwhURivXx0,5710
+evalscope/models/register.py,sha256=4vX6AfScAzwD7UkncbuejfAiQHznQkK5hvtG6jEUbWo,809
+evalscope/models/server_adapter.py,sha256=dS_o9_iC8QY73AehIekYwBQieFECZ97JRfbfleJ-Dtk,6845
 evalscope/models/custom/__init__.py,sha256=wb6f_Bi39s5sj-VO7EXRDXB2WhyFb49BUtEMk77ksNQ,102
 evalscope/models/custom/custom_model.py,sha256=rBQLAuPEw_OPUtRSCEmxEfpcA8jPj8bAdsmtKs4ygus,1566
 evalscope/models/custom/dummy_model.py,sha256=ODD6pt9FvZq_a54oYsehBDslRKHOsk9zsC9iAZvi5Yg,2020
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/arguments.py,sha256=3az0usVSjz0CCcDxNkHFm4mMb8tw6cE3qIAnvhLxos4,9430
-evalscope/perf/benchmark.py,sha256=qNgDNseW8N0beuAB_4-JVtTdHs7ZaJEHK5XnkMU9vRU,9618
-evalscope/perf/http_client.py,sha256=qHIhsSUXHbh5HGqW9JmTJs1O8yrIYVXzSOgXwWlqiyA,7109
-evalscope/perf/main.py,sha256=SUMz8S2XPL8JaSL1-vy8qkrb34d5vp6DfQdwIGOUXTk,1277
+evalscope/perf/arguments.py,sha256=u3GNdnOBmiEirtgJLspsLO7qBwHeWLoXd4vlt69jJ-g,9717
+evalscope/perf/benchmark.py,sha256=hKN-Nu-x-VTswHP0M6PT3jvduWxN7AJpz34DBrUcafQ,9734
+evalscope/perf/http_client.py,sha256=xMakdQkJ2cgIOd-yOmHEW0vbGKTJ0JWhLFt9IFtUP8Q,7473
+evalscope/perf/main.py,sha256=aZUrfbz-Pl2xe8AgUL_6rW6n8dX4YAToDw5xPpLtbI4,1278
 evalscope/perf/plugin/__init__.py,sha256=1sl5s-csrwKb_LVTnpF3HqArz06TRD5LYJ0hpqvokUA,85
 evalscope/perf/plugin/registry.py,sha256=w1IAt6GDdluzSYK5i-yrntvx3_EvIIqJamEL0xZv3zA,1323
 evalscope/perf/plugin/api/__init__.py,sha256=Ckzbq4CkSMVQTedQcDHCYlRd6FTwQAElt2mHB-VXJac,195
@@ -211,7 +232,7 @@ evalscope/perf/plugin/datasets/longalpaca.py,sha256=2aENqCly_DX1dyNcurYsLFJIvXYF
 evalscope/perf/plugin/datasets/openqa.py,sha256=2pv7yyPSFYTjPhvAGBsHl0eQO8gt7Wk1CaKcfTi3Tnc,1394
 evalscope/perf/plugin/datasets/speed_benchmark.py,sha256=ef8MXhT6756y6LsXSpYeWjmwswu2hRXe2BOVS2_OgVM,1968
 evalscope/perf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/utils/analysis_result.py,sha256=ig0zPwbUODGh1GUr3GmnNF4lJJp9SQvW0awWiXEIkCI,1212
+evalscope/perf/utils/analysis_result.py,sha256=ESzaZHGTpr2LoJR3jpOzqMphxSrr79d364ZzD159PmY,1169
 evalscope/perf/utils/benchmark_util.py,sha256=4TyQ_tE5odcjKDFDueI3jrC0vld6QxmTreOd5_SP4vE,5802
 evalscope/perf/utils/db_util.py,sha256=PSBq16uWyzXx0zyoEE4wazWKN19UAA8_GjobS7rTPso,9001
 evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
@@ -238,8 +259,8 @@ evalscope/registry/tasks/gsm8k.yaml,sha256=M2I7otwOSy0usD8yG8d6QziASQlKdhKLflRHM
 evalscope/registry/tasks/mmlu.yaml,sha256=cJcMH1Cvgo9PlYoTmeGx2bcZayysltaa6ehK57dDkvo,726
 evalscope/registry/tasks/mmlu_mini.yaml,sha256=K8ouHh7ve5ZsbkqRtV3Jl-DF01YFPuObfwEdACJA4Pk,778
 evalscope/report/__init__.py,sha256=0Wes3ot2hy9s-WwZaBztst8qkNrXkOF-Hwa1WW1e8lY,260
-evalscope/report/app.py,sha256=lwyeDfxgzTbvy4TXtGYtkBegn33zcAuR0_776i5E2fw,26812
-evalscope/report/combinator.py,sha256=bi6nvTbMrzraZ8kUZ6mIMikk8-qEIVYUhdaH4RE1Tg8,2653
+evalscope/report/app.py,sha256=cvof2Nm4ORxC4D3L22Kg3Ngu3kJwBZlfnFJkwDMCmSQ,26881
+evalscope/report/combinator.py,sha256=O3QirwtYhDhdaWVT4STJMCGZMwoX8BTeJ3HtS9iwnWQ,2567
 evalscope/report/generator.py,sha256=2DULY9W8QCUxdtyfNjo8XAP_YxI1LgR95jknK__kYPU,3600
 evalscope/report/utils.py,sha256=DRlbjbqHEmM8rGlA4pwtlHFhOZtyUzcqiS-mejfIDkU,4584
 evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -248,7 +269,7 @@ evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u
 evalscope/third_party/longbench_write/default_task.json,sha256=d_NPShtW10Mc02U3pAuxX9hXd09tZw7QJAr1SvrECcM,694
 evalscope/third_party/longbench_write/default_task.yaml,sha256=YjU8EeyH9UtM8e7_fhrwJNChQdszOAcrKmOi--Awvhk,578
 evalscope/third_party/longbench_write/eval.py,sha256=39McZSDHL7bA5Dg-BSyZ4EiAF1nfTiYJAnx5FqbNYok,11265
-evalscope/third_party/longbench_write/infer.py,sha256=bFsOp--8Qn6qQ-NpdLY0bennQGQl5TMGEngvGda8k7g,4937
+evalscope/third_party/longbench_write/infer.py,sha256=32t90zTll6SXH7Wx8QnRFMs6ZUwvpbgYNuawCByzwR0,4971
 evalscope/third_party/longbench_write/longbench_write.py,sha256=nIR1toB1hvUXR7Lrs3xcY9wqaI-bjeADg_Oscf3HdaY,3991
 evalscope/third_party/longbench_write/utils.py,sha256=nd-YslsOyNGAuyBfAWb2pnTMaGLMQ58lbnJJdrCndeI,815
 evalscope/third_party/longbench_write/resources/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -260,12 +281,12 @@ evalscope/third_party/longbench_write/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc
 evalscope/third_party/longbench_write/tools/data_etl.py,sha256=T7a-4PwZg5alZQh-oTi1zjMxjGmVVZYVwSR9-diZlF8,5971
 evalscope/third_party/longbench_write/tools/openai_api.py,sha256=PiIvvDYJkn041SJkLoroXwl1B8TtwpB7licVfqNSeuQ,8168
 evalscope/third_party/thinkbench/__init__.py,sha256=C0aSu71_dc1upUVkKmq2VgDd9plpRcYUdCE6BjUWJcA,110
-evalscope/third_party/thinkbench/eval.py,sha256=P-nNryNKc6DMhD6LLTWnpIzYtfxLh67P9GArtq4jT_U,10988
-evalscope/third_party/thinkbench/infer.py,sha256=-2PeyPurgZSwP_TRBNM-Xg3gwjIWRsn5oX0EpSt-0-A,3140
+evalscope/third_party/thinkbench/eval.py,sha256=76G4LTkxqWCDCyj7Ahjj-qjO1gFem1uDzpRAC27ICl0,18896
+evalscope/third_party/thinkbench/infer.py,sha256=2L4DAJKn3wAhNEKnKudQT60igGOJSKH80FR4nS7DHYk,3952
 evalscope/third_party/thinkbench/resources/critique_template.txt,sha256=d4Egc-qH--4lG8X_EcmgymnuZgiCMbee1M5pt4HrRKA,535
 evalscope/third_party/thinkbench/resources/reformat_template.txt,sha256=zTZyVAzmMBtAwI9lHly9EXsqX471OW-VTg538PDcB30,1775
 evalscope/third_party/thinkbench/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/third_party/thinkbench/tools/llm.py,sha256=PkuUUoVlyWXwOwPoMJIGIl0VQr0N83uNYGkA2rBjpe8,1333
+evalscope/third_party/thinkbench/tools/llm.py,sha256=HCFh58_THsVrFVzvGoThwWRu8EbPXD0DotLQEj5u4Tg,1353
 evalscope/third_party/thinkbench/tools/utils.py,sha256=rDu2GVTK4ji9Yh9RLVksZqrfurQsSuN9GW3QCKJ60ng,401
 evalscope/third_party/toolbench_static/README.md,sha256=Osdnt0_K-setbmYwDPCPRp2LXxamGp2mE8KsOByPPOY,3944
 evalscope/third_party/toolbench_static/__init__.py,sha256=BO936RxwodHr4OEpV6W3S_keC91OfOd41_msIJ2d0fs,128
@@ -276,20 +297,22 @@ evalscope/third_party/toolbench_static/infer.py,sha256=rsADLhEd2IBcC6EI9aD7hSJmo
 evalscope/third_party/toolbench_static/requirements.txt,sha256=OW91Z8hfzh7yQUYgP1Di_E6DgNgGoGP1UcvnqrdCR68,22
 evalscope/third_party/toolbench_static/toolbench_static.py,sha256=ABb9Gy09zMt30tY50AZGxSZ46k3NVEsvuDj6xlLOjeA,1966
 evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=usmVelh0ogBlCtSUL0dqp89w2mAqH1Ptv9MURVoGrc8,1209
+evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=GITEbyiER10Zi-ZWpSqYCdAsiVtNeGK24hvR3kmYn2s,2689
 evalscope/utils/__init__.py,sha256=jLVoGryuqUh4Km9QWWQBzpqkcVNRK0MbwNaSgckqdiU,139
 evalscope/utils/arena_utils.py,sha256=Gf8VpH4C_oF2Abif_QeL0rAP6tvTzsc0gglpdNkUE48,7155
-evalscope/utils/chat_service.py,sha256=eZ8uyVeVFpXZo_uvRFyVhnFyJpL14zcn9UA6K4Ax5J4,8676
+evalscope/utils/chat_service.py,sha256=9LNTT-8KsacOLqnQer8j57e224rwOMbU7txV6re-X-A,8720
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
+evalscope/utils/filters.py,sha256=x_NX40uWMmUsVrAGHCeeV2e63HZZFugWUgdUhk64ivM,1523
 evalscope/utils/io_utils.py,sha256=Tjdgen1FsAA4ArqiUzu734L0Px5NuiS0GKRRiGIzxSA,4192
-evalscope/utils/logger.py,sha256=49F2WDi1g_o8aW8Z29wOt9YHE9LDqkHIgb-d8TVybJY,3635
+evalscope/utils/logger.py,sha256=barHSdtbEu21ynGQj_wS-rd7B02wPPR5AgaWCQzvG4w,3638
 evalscope/utils/model_utils.py,sha256=hB9W334ecAb6553FhooT6_jM0g-tjj6AU48IV3K1CKw,1131
 evalscope/utils/utils.py,sha256=lGvn94ryIzx-7WLNJeuyehNTmINt0jYIjrjW12woPCs,9730
 tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
 tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/cli/test_collection.py,sha256=gx3GySIAPNaLUSf3D3Q3V0WZc21BPdNthIbECHQN0TI,3026
-tests/cli/test_run.py,sha256=VV6XTiNSuQiuw6j_jqPWKgCgouNYt8OFmJr-dFmMFDg,8759
+tests/cli/test_all.py,sha256=1wwXtdjBmWYLhs5TXOJhZBwPm2qd9FYFqQSemXWKNUs,3865
+tests/cli/test_collection.py,sha256=V-_M7ngwekMGqPuI16jjJZyAK2XLE4Z6QTn-8B5ykgU,4071
+tests/cli/test_run.py,sha256=LKWWxT0jaMLtcIl57vnXEFFlzbJpAplFqqwinvAHN8Y,15047
 tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/perf/test_perf.py,sha256=iB8Mg565SfwPsObdAByHYfZNqN71kUtPW7ucmyiOWo8,3025
 tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -302,9 +325,9 @@ tests/swift/test_run_swift_vlm_eval.py,sha256=C8DftjewnZaerQWfERI70bU3sQLWQ-ejZU
 tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=THZEXUOSqm9rWslwJHmZyh-Ytv5c_QKpgRW5J2s_69E,6017
 tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/vlm/test_vlmeval.py,sha256=nzWXjw49SlxXgDnYS9N5JSFtcUp8xPOW2YNNzupvtt4,1806
-evalscope-0.12.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.12.0.dist-info/METADATA,sha256=u2yGTXt6DLWEklbCHuclmS4gpiu6AbdBrosLK8HUOmk,30499
-evalscope-0.12.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.12.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.12.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.12.0.dist-info/RECORD,,
+evalscope-0.13.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-0.13.0.dist-info/METADATA,sha256=0i3SENci2ws_vqdewQAxVUqan-MV1LwJoLLcEZ8ML7w,32870
+evalscope-0.13.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-0.13.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.13.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-0.13.0.dist-info/RECORD,,

tests/cli/test_all.py

@@ -0,0 +1,144 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+from dotenv import dotenv_values
+
+env = dotenv_values('.env')
+
+import os
+import subprocess
+import unittest
+
+from evalscope.config import TaskConfig
+from evalscope.constants import EvalType, JudgeStrategy, OutputType
+from evalscope.run import run_task
+from evalscope.utils import is_module_installed, test_level_list
+from evalscope.utils.logger import get_logger
+
+os.environ['LOG_LEVEL'] = 'DEBUG'
+
+logger = get_logger()
+
+datasets=[
+        # 'iquiz',
+        # 'ifeval',
+        # 'mmlu',
+        # 'mmlu_pro',
+        # 'musr',
+        # 'process_bench',
+        # 'race',
+        # 'trivia_qa',
+        # 'cmmlu',
+        # 'humaneval',
+        # 'gsm8k',
+        # 'bbh',
+        # 'competition_math',
+        # 'math_500',
+        # 'aime24',
+        # 'gpqa',
+        # 'arc',
+        # 'ceval',
+        # 'hellaswag',
+        # 'general_mcq',
+        # 'general_qa',
+        'super_gpqa',
+        'live_code_bench',
+        'simple_qa',
+        'chinese_simpleqa',
+]
+
+dataset_args={
+    'mmlu': {
+        'subset_list': ['elementary_mathematics', 'high_school_european_history', 'nutrition'],
+        'few_shot_num': 0
+    },
+    'mmlu_pro': {
+        'subset_list': ['math', 'health'],
+        'few_shot_num': 4
+    },
+    'ceval': {
+        'subset_list': [
+            'computer_network', 'operating_system', 'computer_architecture'
+        ],
+        'few_shot_num': 0
+    },
+    'cmmlu': {
+        'subset_list': ['elementary_chinese'],
+        'few_shot_num': 0
+    },
+    'bbh': {
+        'subset_list': ['word_sorting', 'movie_recommendation'],
+    },
+    'gpqa': {
+        'subset_list': ['gpqa_diamond'],
+        'few_shot_num': 0,
+    },
+    'humaneval': {
+        'metric_list': ['Pass@1', 'Pass@2', 'Pass@5'],
+    },
+    'competition_math': {
+        'subset_list': ['Level 1']
+    },
+    'math_500': {
+        'subset_list': ['Level 1']
+    },
+    'process_bench': {
+        'subset_list': ['gsm8k'],
+    },
+    'musr': {
+        'subset_list': ['murder_mysteries']
+    },
+    'general_mcq': {
+        'local_path': 'custom_eval/text/mcq',  # 自定义数据集路径
+        'subset_list': [
+            'example'  # 评测数据集名称，上述 *_dev.csv 中的 *
+        ],
+    },
+    'general_qa': {
+        'local_path': 'custom_eval/text/qa',  # 自定义数据集路径
+        'subset_list': [
+            'example',  # 评测数据集名称，上述 *_dev.csv 中的 *
+            # 'test'
+        ],
+        'metric_list': ['AverageBLEU']
+    },
+    'super_gpqa': {
+        'subset_list': ['Philosophy', 'Education'],
+        'few_shot_num': 0
+    },
+    'live_code_bench': {
+        'subset_list': ['v4_v5'],
+        'extra_params': {
+            'start_date': '2024-12-01',
+            'end_date': '2025-01-01'
+        },
+    }
+}
+
+class TestRun(unittest.TestCase):
+    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
+    def test_benchmarks(self):
+        from evalscope.config import TaskConfig
+
+        task_cfg = TaskConfig(
+            model='qwen2.5-7b-instruct',
+            api_url='https://dashscope.aliyuncs.com/compatible-mode/v1',
+            api_key= env.get('DASHSCOPE_API_KEY'),
+            eval_type=EvalType.SERVICE,
+            datasets=datasets,
+            dataset_args=dataset_args,
+            eval_batch_size=32,
+            limit=2,
+            stream=True,
+            generation_config={
+                'temperature': 0,
+                'n': 1,
+                'max_tokens': 4096,
+            },
+            judge_strategy=JudgeStrategy.AUTO,
+            judge_model_args={
+                'model_id': 'qwen2.5-7b-instruct',
+                'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+                'api_key': env.get('DASHSCOPE_API_KEY'),
+            }
+        )
+
+        run_task(task_cfg=task_cfg)

tests/cli/test_collection.py

@@ -1,8 +1,9 @@
 import json
+import os
 import unittest
 
 from evalscope.collections import CollectionSchema, DatasetInfo, WeightedSampler
-from evalscope.constants import EvalType
+from evalscope.constants import EvalType, JudgeStrategy
 from evalscope.utils.io_utils import dump_jsonl_data
 from evalscope.utils.utils import test_level_list
 
@@ -44,7 +45,7 @@ class TestCollection(unittest.TestCase):
         from evalscope import TaskConfig, run_task
 
         task_cfg = TaskConfig(
-            model='Qwen2.5-7B-Instruct',
+            model='Qwen2.5-0.5B-Instruct',
             api_url='http://127.0.0.1:8801/v1/chat/completions',
             api_key='EMPTY',
             eval_type=EvalType.SERVICE,
@@ -55,3 +56,28 @@ class TestCollection(unittest.TestCase):
             }},
         )
         run_task(task_cfg=task_cfg)
+
+
+    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
+    def test_evaluate_collection_with_judge(self):
+        from evalscope import TaskConfig, run_task
+
+        task_cfg = TaskConfig(
+            model='qwen2.5-7b-instruct',
+            api_url='https://dashscope.aliyuncs.com/compatible-mode/v1',
+            api_key= os.getenv('DASHSCOPE_API_KEY'),
+            eval_type=EvalType.SERVICE,
+            datasets=['data_collection'],
+            dataset_args={'data_collection': {
+                'local_path': 'outputs/mixed_data_test.jsonl'
+                # 'local_path': 'outputs/weighted_mixed_data.jsonl'
+            }},
+            limit=10,
+            judge_strategy=JudgeStrategy.LLM_RECALL,
+            judge_model_args={
+                'model_id': 'qwen2.5-7b-instruct',
+                'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+                'api_key': os.getenv('DASHSCOPE_API_KEY'),
+            }
+        )
+        run_task(task_cfg=task_cfg)