evalscope 0.11.0__py3-none-any.whl → 0.12.0__py3-none-any.whl

{evalscope-0.11.0.dist-info → evalscope-0.12.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.11.0
+Version: 0.12.0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -21,6 +21,7 @@ Requires-Dist: accelerate
 Requires-Dist: cachetools
 Requires-Dist: datasets<=3.2.0,>=3.0.0
 Requires-Dist: editdistance
+Requires-Dist: immutabledict
 Requires-Dist: jieba
 Requires-Dist: jsonlines
 Requires-Dist: langdetect
@@ -58,6 +59,7 @@ Requires-Dist: accelerate; extra == "all"
 Requires-Dist: cachetools; extra == "all"
 Requires-Dist: datasets<=3.2.0,>=3.0.0; extra == "all"
 Requires-Dist: editdistance; extra == "all"
+Requires-Dist: immutabledict; extra == "all"
 Requires-Dist: jieba; extra == "all"
 Requires-Dist: jsonlines; extra == "all"
 Requires-Dist: langdetect; extra == "all"
@@ -101,10 +103,10 @@ 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: plotly>=5.23.0; extra == "all"
+Requires-Dist: plotly<6.0.0,>=5.23.0; extra == "all"
 Provides-Extra: app
 Requires-Dist: gradio==5.4.0; extra == "app"
-Requires-Dist: plotly>=5.23.0; extra == "app"
+Requires-Dist: plotly<6.0.0,>=5.23.0; extra == "app"
 Provides-Extra: inner
 Requires-Dist: absl-py; extra == "inner"
 Requires-Dist: accelerate; extra == "inner"
@@ -223,6 +225,9 @@ 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).
+- 🔥 **[2025.02.25]** 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.
 - 🔥 **[2025.01.20]** 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.
@@ -460,7 +465,7 @@ Then, you can use the following command to evaluate the model API service:
 ```shell
 evalscope eval \
  --model qwen2.5 \
- --api-url http://127.0.0.1:8801/v1/chat/completions \
+ --api-url http://127.0.0.1:8801/v1 \
  --api-key EMPTY \
  --eval-type service \
  --datasets gsm8k \

{evalscope-0.11.0.dist-info → evalscope-0.12.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=r8gOMX6i8dWMl_WXLsBdHla7cuauBAyv9apky9VxLsE,4598
-evalscope/config.py,sha256=D7C_K0f0xsfzFUSNSJJUTz3n9tmA6zLDbf8pZ_9ltpw,8600
+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=qfMqVWlUiXEiIJ665p3-IYWknhIeNZkCJe3Yn07Y74U,5692
+evalscope/run.py,sha256=zRdBJEYdQ6JzH94eA7gfkzFAvsn3UFwdrvX_snaqGNU,5702
 evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
 evalscope/summarizer.py,sha256=Wnt8Y61PasOkigo8zMpi1qdFzfETjfnDtCDDQ6VwgDw,5867
-evalscope/version.py,sha256=h6YAZAgeAreWmKtpfr4D6BEvnWZxb1bka9hrpYOO0l8,119
+evalscope/version.py,sha256=RDE_Gbn1y54qtXxjxbZOTLDFSkq__2Zy3rAOwyVrvPs,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
@@ -56,15 +56,16 @@ 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=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/benchmark.py,sha256=Kaes5Bg9_bvFO99-JztNlv_TPg4jH9vMYvnMcb1C_G8,2507
+evalscope/benchmarks/data_adapter.py,sha256=e4mtvzlC8ehQ0N4C5PAGJFv5N9Y42WT-OklwaV-Ex1Y,15239
+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/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/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/bbh/bbh_adapter.py,sha256=37wY3r1qW5qdjyKF-8n7UIM0IVcpaQugMb5Rkjbppxg,8524
+evalscope/benchmarks/bbh/bbh_adapter.py,sha256=cep-Ws9Tozju6JWls1-oz3lKYqTL8q8Cee_d-d3cLIo,8407
 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
@@ -101,19 +102,19 @@ evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=1RmhI0SNxHK-Fz-iTIR76zeBRDLlm
 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=i0E4TNajMVcWT8lc5haIjKvdmHuI5qzgpssIm5Fw7bs,7413
+evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=_vGkfgP5ZnQh3AlbJqycQOL_gQHayazMYFzHVo2e5O8,6902
 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_mcq/general_mcq_adapter.py,sha256=M-PocYW4pkGtKOKvFZW-bIoztcGvmHn5Gf5o7F71xCg,5248
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=fu14ZzGYyg2MEdJbxZGBoIbais6xA9Um2BEAJTvBZZM,3823
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=_t2ZNsQzY5AuOOBXkEVNGIB3pZgLKQmw7-5gEqR_Z_k,3848
 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=tiy8Cn1ZmNKjVg8lqNAxWBbsKp8h0uiDNpWuHfcID0A,4689
+evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=1zI6GWfvPiKaZg39N7pSFw2R-GpbrjEo-11K_waq6Dg,4686
 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=4qtMX_SfqkXRMgGLOA6tNGMK9EkITWbjLlJT9gWbT20,10664
+evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=X7fu2mx911Al-7a6j-mJQ3vqTb0cN0u7FoJTrNf6AN4,10661
 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
@@ -121,7 +122,7 @@ evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0
 evalscope/benchmarks/humaneval/humaneval.py,sha256=2Exsg6u8FEu0buADY2tETJluSM8tWacvX06nykKKLSE,3395
 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=3HsAdNj5JJGCFA17sPXi-59yv-pfcB0UeXKdY_mQcwU,2015
+evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=zmN69NDhBR3NJak1cB0z3DqPMuoAvqADWMapQPnvGLs,2025
 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
@@ -129,13 +130,18 @@ evalscope/benchmarks/ifeval/utils.py,sha256=TKrM1m2qDCUauahogItDdICf4mDk0OjasSxg
 evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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/math_500/math_500_adapter.py,sha256=OO3Jx1WuyEMfd4R5znG9_O5ln_SbVVGB5u1bTjiuWaU,2104
 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/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=Fdrj26MfYmPzio2tI23WTcofrwD69_m41mkVpvlxzVU,4815
+evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=73TLdWlEAulZNA0ZMLDQnaXs435vG-gD89yjURjsjpo,4111
+evalscope/benchmarks/musr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/musr/musr_adapter.py,sha256=D-CZMTr9Ld_tJxZdCDPZQxDX86BgJqKWCyy5-tlcONY,2343
+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/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
@@ -146,27 +152,27 @@ evalscope/benchmarks/trivia_qa/trivia_qa.py,sha256=eekxaXppMLb5tCQqNLOw2MaWlYDhI
 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=6rT1zuQh0nLuYymcchO-cMP98EY0vWizbfTfnUERWgo,12905
+evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=MYMLpIEv3oqRiOgAydqM0ZlzpvbzpCymOKUbca98yxo,12915
 evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
 evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
-evalscope/cli/start_app.py,sha256=_NTmCd15tZOROAnPacGWirMS4OXHrL3n2eZj1kokpks,758
-evalscope/cli/start_eval.py,sha256=2lyD2WSQ0DnP6T31VvTimQ-6POnwxeEP9GLPFnT7Tfo,767
-evalscope/cli/start_perf.py,sha256=lEHJBSpzNsO4KGlWfQc-EfZGXq1M_FpOwtRxRdb4fso,813
+evalscope/cli/start_app.py,sha256=WTbba_Iitz1jkQ5n6KHRH-i3U7qJIM7iCi4a9roWjaA,808
+evalscope/cli/start_eval.py,sha256=MXhVDeaMFd6ny88-gnVtQflH660UaDj240YGYnHccx8,775
+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=FJx3KGdLi0-TIqWC_067HEmA4P298BKdwHIrbcai46M,12065
+evalscope/collections/evaluator.py,sha256=1bz2jEgOlv7qHeCgkFCtd1MPWhMa6XnZfP4XJBhTnUc,12321
 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=E0NiP5O56WbF8eiUmw9IY2ouotRog9H-2SRyTzZld0I,17569
+evalscope/evaluator/evaluator.py,sha256=VIiw1eI46UOsFWNd7schD4ah_Q5ll0crl2sRmGIRmig,17649
 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/__init__.py,sha256=SWvqzUzdryW5URz6u4fPkP9XSyA09nQ8zBeE8BbchSg,349
 evalscope/metrics/code_metric.py,sha256=EXE2BZAc9JJT_cpd6eCb0Jo9wwtnzXzHBZxmLzG5Jpw,3300
 evalscope/metrics/math_parser.py,sha256=uTDudn305G3b8-GboWTrDE6OfrEwAW-areHnoGXZ6Is,17302
-evalscope/metrics/metrics.py,sha256=r4FHyEvvFhMu0vAHBw-ByFefObDBC3DQdr53klSk6Wk,13325
+evalscope/metrics/metrics.py,sha256=_YI7RhxlFu_JOgeE3LF9UKu6mJruvyu4FgqVf78Bjb8,13813
 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
@@ -174,20 +180,20 @@ evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=Kq6AObenmLVQ5tN3NgN
 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=fT3i8c9jRmz_VBcUYMMmXrlCM6JWcixPdgak5yT6Wkw,2177
-evalscope/models/chat_adapter.py,sha256=nOrNDuvuNKkTcW9zNcR_EIqbzkqK5PFws-5YsSxBR9E,6120
+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/local_model.py,sha256=s0YVX9Djqazusk7qzSpWQB76jGGuzJxqQlZzomsCFsk,2621
+evalscope/models/local_model.py,sha256=yydggBCLcBAmUWbBhv7o2CA3RbG0DwDZharPdrkbNcg,2628
 evalscope/models/model.py,sha256=diu4TE1ZFWdynTxsl4DejTNsLdwjxoyj2nsKR-Y8EZE,7343
-evalscope/models/server_adapter.py,sha256=iVJuUJlHGVGxnlrDMnbHZ8WQ4OR2HK5HrXH4obD2_cg,4173
+evalscope/models/server_adapter.py,sha256=l_EI1jTaH1EBATKaH1USAdiYkezz7IYUQTwhURivXx0,5710
 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=rgSXzxIJ67yB_SLUdl4ljem2-ilB-Gw3640f4KWLO1k,51
-evalscope/perf/arguments.py,sha256=8KiD4u51B_twEaIiI0_kw4Jknk3YG4S6XN-vgvutChA,9233
+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=TfnQT9OaBlUCpGwi4ifSJBaaGsn3P2KVBPMGuw-Rqkk,7073
+evalscope/perf/http_client.py,sha256=qHIhsSUXHbh5HGqW9JmTJs1O8yrIYVXzSOgXwWlqiyA,7109
 evalscope/perf/main.py,sha256=SUMz8S2XPL8JaSL1-vy8qkrb34d5vp6DfQdwIGOUXTk,1277
 evalscope/perf/plugin/__init__.py,sha256=1sl5s-csrwKb_LVTnpF3HqArz06TRD5LYJ0hpqvokUA,85
 evalscope/perf/plugin/registry.py,sha256=w1IAt6GDdluzSYK5i-yrntvx3_EvIIqJamEL0xZv3zA,1323
@@ -195,7 +201,7 @@ evalscope/perf/plugin/api/__init__.py,sha256=Ckzbq4CkSMVQTedQcDHCYlRd6FTwQAElt2m
 evalscope/perf/plugin/api/base.py,sha256=B_H04qKx7eRTn155rnDrbTYur7PK1mvxfQKYcqYbndU,2118
 evalscope/perf/plugin/api/custom_api.py,sha256=ay1AGi4y2opjwyRl0J0A54-vLB-pBj3QBFkzog0KA-g,3787
 evalscope/perf/plugin/api/dashscope_api.py,sha256=V5fwn-p_fLH0dWKzhN9TvYSHRgla4INfXC4NDaIjoQ8,3825
-evalscope/perf/plugin/api/openai_api.py,sha256=JxQGlzAbM7MBWcr3MvWiAg6E4lqdQLfkk1qK0vUWvn8,6817
+evalscope/perf/plugin/api/openai_api.py,sha256=KQRQMOfQceKQtrvTE-SyhNHcDoGuQ0900yh7r74Hcoo,7560
 evalscope/perf/plugin/datasets/__init__.py,sha256=9mz2TnVHhxbEKAS9pLbKMQuIoShNlZpGiRo9e2RQLUs,490
 evalscope/perf/plugin/datasets/base.py,sha256=Z-INWueeYjfEZhP4lbTlBMVwIa6BcXZKWx-w7Pop3mA,1786
 evalscope/perf/plugin/datasets/custom.py,sha256=_GSC5yR90_BjcRjdJqrJT2vHQAzskz5XxYOxngUM2Pg,815
@@ -206,7 +212,7 @@ evalscope/perf/plugin/datasets/openqa.py,sha256=2pv7yyPSFYTjPhvAGBsHl0eQO8gt7Wk1
 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/benchmark_util.py,sha256=T_pXpSCwCNLJgfzgv3IO7kG61ghTLthVMsXZhBCGP_4,5541
+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
 evalscope/perf/utils/local_server.py,sha256=clF8i0UFmaxBBB6gX05KvVCyzSv0xzsAidz0_sLLlAk,4627
@@ -232,7 +238,7 @@ 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=adP1rVVOxYMbCTdopV3FKWBhUzB7t1AXcDOxW4Ct56g,26647
+evalscope/report/app.py,sha256=lwyeDfxgzTbvy4TXtGYtkBegn33zcAuR0_776i5E2fw,26812
 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
@@ -253,6 +259,14 @@ evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl,sha256=odT
 evalscope/third_party/longbench_write/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 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/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/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
 evalscope/third_party/toolbench_static/config_default.json,sha256=KrUzeHL2DNiM5FwY7cH3KZlxTwELCQZ6e39nilfUi0M,368
@@ -269,13 +283,13 @@ evalscope/utils/chat_service.py,sha256=eZ8uyVeVFpXZo_uvRFyVhnFyJpL14zcn9UA6K4Ax5
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
 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
+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=gtId2SF1LlDCIn4S_WKRpAyTig_pWOhY8yto4P5B1EY,8303
+tests/cli/test_run.py,sha256=VV6XTiNSuQiuw6j_jqPWKgCgouNYt8OFmJr-dFmMFDg,8759
 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
@@ -288,9 +302,9 @@ 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-0.11.0.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,,
+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,,

tests/cli/test_run.py

@@ -76,10 +76,10 @@ class TestRun(unittest.TestCase):
                         # 'mmlu_pro',
                         # 'bbh',
                         # 'hellaswag',
-                        # 'gsm8k',
+                        'gsm8k',
                         # 'arc',
                         # 'race',
-                        'ifeval',
+                        # 'ifeval',
                         # 'truthful_qa',
                         # 'trivia_qa',
                         ],
@@ -101,7 +101,8 @@ class TestRun(unittest.TestCase):
                     '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 *
-                    ]
+                    ],
+                    'query_template': 'Question: {question}\n{choices}\nAnswer: {answer}'  # 问题模板
                 },
                 'general_qa': {
                     'local_path': 'custom_eval/text/qa',  # 自定义数据集路径
@@ -111,7 +112,8 @@ class TestRun(unittest.TestCase):
                 }
             },
         )
-        run_task(task_cfg=task_cfg)
+        res = run_task(task_cfg=task_cfg)
+        print(res)
 
     @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
     def test_run_humaneval(self):
@@ -140,24 +142,26 @@ class TestRun(unittest.TestCase):
 
         task_cfg = TaskConfig(
             model='Qwen2.5-0.5B-Instruct',
-            api_url='http://127.0.0.1:8801/v1/chat/completions',
+            api_url='http://127.0.0.1:8801/v1',
             api_key='EMPTY',
             eval_type=EvalType.SERVICE,
             datasets=[
-                # 'iquiz',
+                'iquiz',
                 # 'ifeval',
                 # 'mmlu',
                 # 'mmlu_pro',
+                # 'musr',
+                # 'process_bench',
                 # 'race',
                 # 'trivia_qa',
                 # 'cmmlu',
                 # 'humaneval',
                 # 'gsm8k',
                 # 'bbh',
-                'competition_math',
-                'math_500',
-                'aime24',
-                'gpqa',
+                # 'competition_math',
+                # 'math_500',
+                # 'aime24',
+                # 'gpqa',
                 # 'arc',
                 # 'ceval',
                 # 'hellaswag',
@@ -168,8 +172,8 @@ class TestRun(unittest.TestCase):
                     'few_shot_num': 0
                 },
                 'mmlu_pro': {
-                    'subset_list': ['math'],
-                    'few_shot_num': 0
+                    'subset_list': ['math', 'health'],
+                    'few_shot_num': 4
                 },
                 'ceval': {
                     'subset_list': [
@@ -194,15 +198,23 @@ class TestRun(unittest.TestCase):
                 'competition_math': {
                     'subset_list': ['Level 1']
                 },
+                'process_bench': {
+                    'subset_list': ['gsm8k'],
+                },
+                'musr': {
+                    'subset_list': ['murder_mysteries']
+                },
             },
             eval_batch_size=5,
-            limit=10,
+            limit=5,
             debug=True,
+            stream=True,
             generation_config={
                 'temperature': 0.7,
-                'n': 5
+                'n': 1,
+                'max_tokens': 512,
             },
-            use_cache='/mnt/data/data/user/maoyunlin.myl/eval-scope/outputs/20250212_150525'
+            # use_cache='/mnt/data/data/user/maoyunlin.myl/eval-scope/outputs/20250212_150525',
         )
 
         run_task(task_cfg=task_cfg)