evalscope 0.10.1__py3-none-any.whl → 0.11.0__py3-none-any.whl

{evalscope-0.10.1.dist-info → evalscope-0.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.10.1
+Version: 0.11.0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -19,10 +19,12 @@ License-File: LICENSE
 Requires-Dist: absl-py
 Requires-Dist: accelerate
 Requires-Dist: cachetools
-Requires-Dist: datasets<=3.0.1,>=3.0.0
+Requires-Dist: datasets<=3.2.0,>=3.0.0
 Requires-Dist: editdistance
 Requires-Dist: jieba
 Requires-Dist: jsonlines
+Requires-Dist: langdetect
+Requires-Dist: latex2sympy2
 Requires-Dist: matplotlib
 Requires-Dist: modelscope[framework]
 Requires-Dist: nltk>=3.9
@@ -42,20 +44,24 @@ Requires-Dist: scikit-learn
 Requires-Dist: seaborn
 Requires-Dist: sentencepiece
 Requires-Dist: simple-ddl-parser
+Requires-Dist: sympy
 Requires-Dist: tabulate
 Requires-Dist: tiktoken
 Requires-Dist: torch
 Requires-Dist: tqdm
 Requires-Dist: transformers>=4.33
 Requires-Dist: transformers-stream-generator
+Requires-Dist: word2number
 Provides-Extra: all
 Requires-Dist: absl-py; extra == "all"
 Requires-Dist: accelerate; extra == "all"
 Requires-Dist: cachetools; extra == "all"
-Requires-Dist: datasets<=3.0.1,>=3.0.0; extra == "all"
+Requires-Dist: datasets<=3.2.0,>=3.0.0; extra == "all"
 Requires-Dist: editdistance; extra == "all"
 Requires-Dist: jieba; extra == "all"
 Requires-Dist: jsonlines; extra == "all"
+Requires-Dist: langdetect; extra == "all"
+Requires-Dist: latex2sympy2; extra == "all"
 Requires-Dist: matplotlib; extra == "all"
 Requires-Dist: modelscope[framework]; extra == "all"
 Requires-Dist: nltk>=3.9; extra == "all"
@@ -75,12 +81,14 @@ Requires-Dist: scikit-learn; extra == "all"
 Requires-Dist: seaborn; extra == "all"
 Requires-Dist: sentencepiece; extra == "all"
 Requires-Dist: simple-ddl-parser; extra == "all"
+Requires-Dist: sympy; extra == "all"
 Requires-Dist: tabulate; extra == "all"
 Requires-Dist: tiktoken; extra == "all"
 Requires-Dist: torch; extra == "all"
 Requires-Dist: tqdm; extra == "all"
 Requires-Dist: transformers>=4.33; extra == "all"
 Requires-Dist: transformers-stream-generator; extra == "all"
+Requires-Dist: word2number; extra == "all"
 Requires-Dist: ms-opencompass>=0.1.4; extra == "all"
 Requires-Dist: ms-vlmeval>=0.0.9; extra == "all"
 Requires-Dist: mteb==1.19.4; extra == "all"
@@ -92,10 +100,10 @@ Requires-Dist: numpy; extra == "all"
 Requires-Dist: sse-starlette; extra == "all"
 Requires-Dist: transformers; extra == "all"
 Requires-Dist: unicorn; extra == "all"
-Requires-Dist: gradio>=5.4.0; extra == "all"
+Requires-Dist: gradio==5.4.0; extra == "all"
 Requires-Dist: plotly>=5.23.0; extra == "all"
 Provides-Extra: app
-Requires-Dist: gradio>=5.4.0; extra == "app"
+Requires-Dist: gradio==5.4.0; extra == "app"
 Requires-Dist: plotly>=5.23.0; extra == "app"
 Provides-Extra: inner
 Requires-Dist: absl-py; extra == "inner"
@@ -215,6 +223,7 @@ Please scan the QR code below to join our community groups:
 
 
 ## 🎉 News
+- 🔥 **[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.
 - 🔥 **[2025.01.20]** 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-0.10.1.dist-info → evalscope-0.11.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=v6IyhjgBACDkapnZYi6DeBI1aZxRVA-mx7KR1j72lYs,4493
-evalscope/config.py,sha256=4klkNziKT4r8a4Z1imkiY16-S8iER1BYPMOG4nJg9lU,8571
+evalscope/arguments.py,sha256=r8gOMX6i8dWMl_WXLsBdHla7cuauBAyv9apky9VxLsE,4598
+evalscope/config.py,sha256=D7C_K0f0xsfzFUSNSJJUTz3n9tmA6zLDbf8pZ_9ltpw,8600
 evalscope/constants.py,sha256=bkcDVbB4Pr1Qxz83qefcWjEetVGiHTcx3m84WX14ASI,3330
-evalscope/run.py,sha256=KKZBy2hr8_BscE0ZR1rN9U7iPc1eZYeeInfXe3EY7lA,5718
+evalscope/run.py,sha256=qfMqVWlUiXEiIJ665p3-IYWknhIeNZkCJe3Yn07Y74U,5692
 evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
 evalscope/summarizer.py,sha256=Wnt8Y61PasOkigo8zMpi1qdFzfETjfnDtCDDQ6VwgDw,5867
-evalscope/version.py,sha256=Bt6Ke7m38AQOnf3xTgdKX-eFqm09Gu5GYEjTkjPrPEk,119
+evalscope/version.py,sha256=h6YAZAgeAreWmKtpfr4D6BEvnWZxb1bka9hrpYOO0l8,119
 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
@@ -56,13 +56,15 @@ 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=SFDjyxd4t4KEcLBP82zE_KCJ_wXuv8J3XFzIR4M9fFI,2419
-evalscope/benchmarks/data_adapter.py,sha256=Aaspp5dR1aINXAopm0y7LHeMwJbmYXfy5bNm9DpagRo,12051
+evalscope/benchmarks/benchmark.py,sha256=IY2xYmNR58aYnZK7rnUDONWiLQopo_ZifGS2SfN2L-Q,2422
+evalscope/benchmarks/data_adapter.py,sha256=xCBvJe4ubgpP1J8ElcWAJwF6B5CSrBEv_uMwQzlUaLY,12540
+evalscope/benchmarks/aime24/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/aime24/aime24_adapter.py,sha256=FYH8NsT1nis3VoBMzRM_ueOsGNXjOKZCa6J_wpUM3RQ,1772
 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=TdDB3lazJNdUt2bBo1G7zaOAN6YkKXdcgMui1ygQj3Y,6591
+evalscope/benchmarks/arc/arc_adapter.py,sha256=vfwAy01LA141qn1lsSyZmEIGWbbhOCRMOGoSM-K2z6M,6490
 evalscope/benchmarks/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/bbh/bbh_adapter.py,sha256=pkgIEr_4QyzngUcs0j4oOscFljGoYZcCAS861Afnt_0,8316
+evalscope/benchmarks/bbh/bbh_adapter.py,sha256=37wY3r1qW5qdjyKF-8n7UIM0IVcpaQugMb5Rkjbppxg,8524
 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
@@ -91,55 +93,60 @@ 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=2PvM5cvviyVNeFGnz-ymYVhEyPoea52OL_dg7dwVzQQ,11429
+evalscope/benchmarks/ceval/ceval_adapter.py,sha256=Qz2oNGw0H_4FtfY-Izdxv9fgwxScJksyvwzeQw-aVyo,11374
 evalscope/benchmarks/ceval/ceval_exam.py,sha256=ngOvb6Fymt7iPWIb2fzrUVpqmUT2VBoqh7X_IH8Bcsc,4824
-evalscope/benchmarks/ceval/samples.jsonl,sha256=dyWhGAdt4eq6Amgu2Ykx8RevUJVFtbhGFSTbDAeUgHc,448
 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=O6FIsJDgg4OiHZSafaDq7jZ2gubWumPMhkdVb8WN-D8,10526
+evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=1RmhI0SNxHK-Fz-iTIR76zeBRDLlm0m6_7rJywqk3Rk,10446
 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=ns2WPbqkR52rRKo244WoAeAO9VOESEl_sHCPhym2DnM,6768
+evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=i0E4TNajMVcWT8lc5haIjKvdmHuI5qzgpssIm5Fw7bs,7413
+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/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=vDHgsWpsIZQWNadl3mI8M3rDKkvPM2N2KAkW-8aeOHY,5130
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=1MQXl3Wf_Dnzn7_7BSTu7RT6BOfhhiVyAnqECawxyfM,3899
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=fu14ZzGYyg2MEdJbxZGBoIbais6xA9Um2BEAJTvBZZM,3823
 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=Z5TtgPCCT8AVmFCMVIVmfhqe51CyCTaLSYTiev7smPw,4232
+evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=tiy8Cn1ZmNKjVg8lqNAxWBbsKp8h0uiDNpWuHfcID0A,4689
 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=9DuNos8xCOVFOUSJ04LAoBRVPbtqgR4XmOVk6r8ADU8,11114
+evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=4qtMX_SfqkXRMgGLOA6tNGMK9EkITWbjLlJT9gWbT20,10664
 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=p7Nu-1B2mgbjfth1IhkMSWEC0TxOtD6tp_bOWeeRjts,6332
+evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=qArX2umdrYJZkDA9i3XGBGljCton99v5Yss9be9iZYw,6269
 evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/humaneval/humaneval.py,sha256=2Exsg6u8FEu0buADY2tETJluSM8tWacvX06nykKKLSE,3395
-evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=mjWkJqeRM1JVlrLXaCz1qscneLhYySZt8cgdXZSmJWY,5215
+evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=onacZB_6SF9239Ly-U70__WYsinS9iWpnf3oiYMNxKc,5164
 evalscope/benchmarks/ifeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=Jx04TddVZE1gk4wXyljhtt3CLo-7Ux_RcLLMlTV-Nhg,2024
+evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=3HsAdNj5JJGCFA17sPXi-59yv-pfcB0UeXKdY_mQcwU,2015
 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=gByj-11KGRTQk2wF1UwNACl8i1svBAEDaj-KJm1XEmw,2387
+evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=nv4mzKOPp1YPcr6e7daZuZyQ3jRNNG6PUzi38REuwSk,2356
+evalscope/benchmarks/math_500/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/math_500/math_500_adapter.py,sha256=mBzsllop5sTHw-uK04FjhEWDiEDjDaNUFDUBIVN7Xgg,1742
 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=-ONQW0EPAPXFPIpH_Y6zRE-t9j5dT7yABgAU8wxIH4M,11829
+evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=pmT1y9dbWJcZK3U6hkXa3-lBDABx7DhQ7oHc3O-Nkg0,11769
 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=9Mg7AKb2YL7aCilsXNA5_f1JmETfXQd1kOvLkGcKFEA,4372
+evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=Fdrj26MfYmPzio2tI23WTcofrwD69_m41mkVpvlxzVU,4815
 evalscope/benchmarks/race/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO61nU,3608
-evalscope/benchmarks/race/race_adapter.py,sha256=9uyQLDA9kVKGu0XhwcBoMyxcgUh3jqWXRO5DahRqUpg,6678
+evalscope/benchmarks/race/race_adapter.py,sha256=dC9I-3T9UFh2OVpmWKRmSszPOlFZAZ40xOPa4zN3daI,6661
 evalscope/benchmarks/race/samples.jsonl,sha256=bhSktBgU6axYQCClRtQ7nN8D1x815AU8xMAIG1oflG0,1243
 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=e-jrcCvl8fbPzWCOYKq_sbl4XCulsPzAECGtvTPE-rM,5106
+evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=GVuJT-Xz4ugVtcUSTRxcBgViHVowcqJf3yVsotcZoZI,5062
 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=tCVO0RTD_S7z1ky7su5z67dnpgbsEtcH5j0vCpfvUV8,12908
+evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=6rT1zuQh0nLuYymcchO-cMP98EY0vWizbfTfnUERWgo,12905
 evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
 evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
@@ -148,19 +155,19 @@ evalscope/cli/start_eval.py,sha256=2lyD2WSQ0DnP6T31VvTimQ-6POnwxeEP9GLPFnT7Tfo,7
 evalscope/cli/start_perf.py,sha256=lEHJBSpzNsO4KGlWfQc-EfZGXq1M_FpOwtRxRdb4fso,813
 evalscope/cli/start_server.py,sha256=DQRIfbsHaOAsVcLGF6iRyJnxmd5Sf_tgytpJNfiWCeE,3662
 evalscope/collections/__init__.py,sha256=hd68Qf-ryeDsz5Pu-Dh83M5V5RE5mhLsG-vc55n5n0o,228
-evalscope/collections/evaluator.py,sha256=_XaLn_cSKvAW96aNwaaPbrBDPl9qn0VrsTjID_y7SpM,8910
-evalscope/collections/sampler.py,sha256=6Tp0jN7bJQqG-7AQ2UDPDur6O5aC_nl0N-OV9HfuE9Q,4769
-evalscope/collections/schema.py,sha256=Ns47HXt7Ym4sPdPyxStxALHUid2cW7kWhqvw_jK_p-4,4172
+evalscope/collections/evaluator.py,sha256=FJx3KGdLi0-TIqWC_067HEmA4P298BKdwHIrbcai46M,12065
+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=0IOuWQ4KgWuMisNmFqh4-id3d1Kkbkf4JW-6hVz7tqU,16638
+evalscope/evaluator/evaluator.py,sha256=E0NiP5O56WbF8eiUmw9IY2ouotRog9H-2SRyTzZld0I,17569
 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=yzuZjXufrPqVhzNTNaJLJwhs7-Sgb-iNG0I3BdOX7Tg,291
 evalscope/metrics/code_metric.py,sha256=EXE2BZAc9JJT_cpd6eCb0Jo9wwtnzXzHBZxmLzG5Jpw,3300
-evalscope/metrics/math_accuracy.py,sha256=a0L_YT70bsJYn5_POICJyj6ZVFbHek1ly6j_ssV9Xsc,5585
-evalscope/metrics/metrics.py,sha256=H02Hhj9Me2qzUjSzdV57i5Gj6xP_w5kbuPcuPpejlI0,12860
-evalscope/metrics/named_metrics.py,sha256=j-y-d5EJ4FJzOxlIKobKIMUNu--nzAIIc2j0TvDfFb0,574
+evalscope/metrics/math_parser.py,sha256=uTDudn305G3b8-GboWTrDE6OfrEwAW-areHnoGXZ6Is,17302
+evalscope/metrics/metrics.py,sha256=r4FHyEvvFhMu0vAHBw-ByFefObDBC3DQdr53klSk6Wk,13325
+evalscope/metrics/named_metrics.py,sha256=SeBXmgWyK4y4tKiGKro3k-CZU1OShuKe6qxwpT3tizY,1313
 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
@@ -168,12 +175,12 @@ evalscope/metrics/resources/gpt2-zhcn3-v4.bpe,sha256=J_K-oSt9usFEw87Av6j7ETn3J48
 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=fT3i8c9jRmz_VBcUYMMmXrlCM6JWcixPdgak5yT6Wkw,2177
-evalscope/models/chat_adapter.py,sha256=9DIMwacjrR647pYVKgeYn090ZKBVHmMD_mf3Gz2vdw0,5461
-evalscope/models/choice_adapter.py,sha256=Zb-UUFpF2tpMGuGH_wFleMxpSb__-SuN1cMF7yj25aI,7661
-evalscope/models/custom_adapter.py,sha256=uj4kbBCwhrXjvSq9f6HgTJ5yJ9FJpvs1k5-9Ekm9RmA,2272
-evalscope/models/local_model.py,sha256=EBclVq5tqUFNOZebRlNnZSvzwtSun7FsZRf2tx0cMt0,2486
+evalscope/models/chat_adapter.py,sha256=nOrNDuvuNKkTcW9zNcR_EIqbzkqK5PFws-5YsSxBR9E,6120
+evalscope/models/choice_adapter.py,sha256=jj_6KB1BAsvv4Yufn2bM2tCiLovFUum2368lseogmb8,8036
+evalscope/models/custom_adapter.py,sha256=Ed_MGEcZxKK4mkXTpUY4GXTsayprHzIEOC1L9gqwjf4,2284
+evalscope/models/local_model.py,sha256=s0YVX9Djqazusk7qzSpWQB76jGGuzJxqQlZzomsCFsk,2621
 evalscope/models/model.py,sha256=diu4TE1ZFWdynTxsl4DejTNsLdwjxoyj2nsKR-Y8EZE,7343
-evalscope/models/server_adapter.py,sha256=VGk_nTwkLWO7Ln7lV_KSaIBzlSRZzyIs_bWDeJ_pOho,4469
+evalscope/models/server_adapter.py,sha256=iVJuUJlHGVGxnlrDMnbHZ8WQ4OR2HK5HrXH4obD2_cg,4173
 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
@@ -225,7 +232,7 @@ 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=kB4CCrAoIONRc37Np8B3QsLxJBD_j2Sw2xtfR1FgfC0,26087
+evalscope/report/app.py,sha256=adP1rVVOxYMbCTdopV3FKWBhUzB7t1AXcDOxW4Ct56g,26647
 evalscope/report/combinator.py,sha256=bi6nvTbMrzraZ8kUZ6mIMikk8-qEIVYUhdaH4RE1Tg8,2653
 evalscope/report/generator.py,sha256=2DULY9W8QCUxdtyfNjo8XAP_YxI1LgR95jknK__kYPU,3600
 evalscope/report/utils.py,sha256=DRlbjbqHEmM8rGlA4pwtlHFhOZtyUzcqiS-mejfIDkU,4584
@@ -258,9 +265,9 @@ evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1
 evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=usmVelh0ogBlCtSUL0dqp89w2mAqH1Ptv9MURVoGrc8,1209
 evalscope/utils/__init__.py,sha256=jLVoGryuqUh4Km9QWWQBzpqkcVNRK0MbwNaSgckqdiU,139
 evalscope/utils/arena_utils.py,sha256=Gf8VpH4C_oF2Abif_QeL0rAP6tvTzsc0gglpdNkUE48,7155
-evalscope/utils/chat_service.py,sha256=Kh3hEUW_HF158a0QqHbWepHIHRQFJgUM-jCDAcQ_maw,8674
+evalscope/utils/chat_service.py,sha256=eZ8uyVeVFpXZo_uvRFyVhnFyJpL14zcn9UA6K4Ax5J4,8676
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
-evalscope/utils/io_utils.py,sha256=vm6uJBBqx4fc7jsHGbwNQ6Hbx7XYhjT1Q2dQ7aHjDD0,4172
+evalscope/utils/io_utils.py,sha256=Tjdgen1FsAA4ArqiUzu734L0Px5NuiS0GKRRiGIzxSA,4192
 evalscope/utils/logger.py,sha256=49F2WDi1g_o8aW8Z29wOt9YHE9LDqkHIgb-d8TVybJY,3635
 evalscope/utils/model_utils.py,sha256=PK7pKNY8ovtGZHNRvDpZ-d8zBHMOkxd6fRVkM8VF06I,736
 evalscope/utils/utils.py,sha256=a6a2vDDxqlj7nY8xynkKkWs_ZPXEU2UMwvxp0JEpHjg,9686
@@ -268,7 +275,7 @@ 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=aywruYPPweMEHaBOynf0G3liKBKMH_H_e4Znq2PcaR4,5821
+tests/cli/test_run.py,sha256=gtId2SF1LlDCIn4S_WKRpAyTig_pWOhY8yto4P5B1EY,8303
 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
@@ -281,9 +288,9 @@ 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-0.10.1.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.10.1.dist-info/METADATA,sha256=-HQt66q9NaZvcNwiXgLW87aduUogXKaHYz6JokxtEXc,28975
-evalscope-0.10.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.10.1.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.10.1.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.10.1.dist-info/RECORD,,
+evalscope-0.11.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-0.11.0.dist-info/METADATA,sha256=GL8Ybyby65DYg8jxjxzdcFYvXBhKzE7eRFIBRiJ0-hc,29584
+evalscope-0.11.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-0.11.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.11.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-0.11.0.dist-info/RECORD,,

tests/cli/test_run.py

@@ -73,16 +73,18 @@ class TestRun(unittest.TestCase):
     def test_run_task(self):
         task_cfg = {'model': 'qwen/Qwen2-0.5B-Instruct',
                     'datasets': [
-                        'mmlu_pro',
+                        # 'mmlu_pro',
                         # 'bbh',
-                        'hellaswag',
+                        # 'hellaswag',
                         # 'gsm8k',
-                        # 'arc'
+                        # 'arc',
                         # 'race',
+                        'ifeval',
                         # 'truthful_qa',
                         # 'trivia_qa',
                         ],
-                    'limit': 20,
+                    'limit': 2,
+                    'eval_batch_size': 2,
                     'debug': True}
         run_task(task_cfg=task_cfg)
 
@@ -93,9 +95,9 @@ class TestRun(unittest.TestCase):
 
         task_cfg = TaskConfig(
             model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['ceval', 'general_qa'],  # 数据格式，选择题格式固定为 'ceval'
+            datasets=['general_mcq', 'general_qa'],  # 数据格式，选择题格式固定为 'ceval'
             dataset_args={
-                'ceval': {
+                '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 *
@@ -117,8 +119,17 @@ class TestRun(unittest.TestCase):
 
         task_cfg = TaskConfig(
             model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['humaneval'],
-            limit=2
+            datasets=[
+                # 'math_500',
+                # 'aime24',
+                'competition_math'
+            ],
+            dataset_args={
+                'competition_math': {
+                    'subset_list': ['Level 4', 'Level 5']
+                }
+            },
+            limit=5
         )
 
         run_task(task_cfg=task_cfg)
@@ -128,12 +139,12 @@ class TestRun(unittest.TestCase):
         from evalscope.config import TaskConfig
 
         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,
             datasets=[
-                'iquiz',
+                # 'iquiz',
                 # 'ifeval',
                 # 'mmlu',
                 # 'mmlu_pro',
@@ -141,25 +152,91 @@ class TestRun(unittest.TestCase):
                 # 'trivia_qa',
                 # 'cmmlu',
                 # 'humaneval',
-                # 'competition_math',
                 # 'gsm8k',
+                # 'bbh',
+                'competition_math',
+                'math_500',
+                'aime24',
+                'gpqa',
                 # 'arc',
                 # 'ceval',
-                # 'bbh',
                 # 'hellaswag',
             ],
             dataset_args={
+                'mmlu': {
+                    'subset_list': ['elementary_mathematics'],
+                    'few_shot_num': 0
+                },
+                'mmlu_pro': {
+                    'subset_list': ['math'],
+                    'few_shot_num': 0
+                },
                 'ceval': {
                     'subset_list': [
-                        'computer_network', 'operating_system', 'computer_architecture', 'college_programming'
-                    ]
-                }
+                        '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']
+                },
+            },
+            eval_batch_size=5,
+            limit=10,
+            debug=True,
+            generation_config={
+                'temperature': 0.7,
+                'n': 5
             },
-            # limit=10
+            use_cache='/mnt/data/data/user/maoyunlin.myl/eval-scope/outputs/20250212_150525'
         )
 
         run_task(task_cfg=task_cfg)
 
 
+    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
+    def test_run_batch_eval(self):
+        from evalscope.config import TaskConfig
+
+        task_cfg = TaskConfig(
+            model='LLM-Research/Llama-3.2-1B-Instruct',
+            datasets=[
+                # 'math_500',
+                # 'aime24',
+                # 'competition_math'
+                # 'arc',
+                'gsm8k'
+                # 'truthful_qa'
+            ],
+            dataset_args={
+                'competition_math': {
+                    'subset_list': ['Level 4', 'Level 5']
+                }
+            },
+            eval_batch_size=2,
+            limit=5,
+            generation_config={
+                'max_new_tokens': 2048,
+                'temperature': 0.7,
+                'num_return_sequences': 2,
+            }
+        )
+
+        run_task(task_cfg=task_cfg)
+
 if __name__ == '__main__':
     unittest.main()

evalscope/benchmarks/ceval/samples.jsonl

@@ -1 +0,0 @@
-{'id': 0, 'question': '下列关于税法基本原则的表述中，不正确的是____。', 'A': '税收法定原则包括税收要件法定原则和税务合法性原则', 'B': '税收公平原则源于法律上的平等性原则', 'C': '税收效率原则包含经济效率和行政效率两个方面', 'D': '税务机关按法定程序依法征税，可以自由做出减征、停征或免征税款的决定', 'answer': 'D', 'explanation': ''}