evalscope 0.15.0__py3-none-any.whl → 0.16.0__py3-none-any.whl

{evalscope-0.15.0.dist-info → evalscope-0.16.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=jywTxu_HWhgf0_OlnaOyRSzUHenr5Zio2vmcCgcfbxg,5453
-evalscope/config.py,sha256=O3kjjVFRGSrlLD5EI4t99Z-m6oFtQVmEudvE62x92wY,9648
+evalscope/arguments.py,sha256=fZW-om5E2_JaFcEmkvahvundjedPLgIDde-zwDXinG0,5868
+evalscope/config.py,sha256=19QaZ5VS8wknt4sLBxiZkR6pH-nm4Ph3Kl-1bZgcQcE,10799
 evalscope/constants.py,sha256=PHnsGndB4N5-jvmawPxMK5b9geE2Es5cUe8ZKYSuKgM,4016
 evalscope/run.py,sha256=_DKbxgQGwhweBnQrI7lQhu5eoz4LYPVeNanzD4lHuJA,6476
 evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
 evalscope/summarizer.py,sha256=61kU5ZoSh1dd8HMJPqP3ZvJwcY9szwWFCZdu2lfATJA,5920
-evalscope/version.py,sha256=X2BkdAHDhsMo9BTAegfd5uYheDVI8rh_UG5YqMwwXUE,119
+evalscope/version.py,sha256=8STVV6Y877B3esrgvovInSk4IFNzxZ_ZEz9ND_6B2lQ,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
@@ -50,27 +50,27 @@ evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py,sha256=6x-4O2pgsjZCVf
 evalscope/backend/rag_eval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/backend/rag_eval/utils/clip.py,sha256=GLHhPCac2AH35AvRLvVqePA1gIMAewHTFmCJCDZzvqU,5015
 evalscope/backend/rag_eval/utils/embedding.py,sha256=tFMepPAMO4Kkqeqh-XxXIDYRjGbCMlk7lwuUW7FNvCA,7977
-evalscope/backend/rag_eval/utils/llm.py,sha256=acaD5QHPJUstJGpW1sNJ-3ZPT5J_Z8beOWb61Rtz07U,2607
+evalscope/backend/rag_eval/utils/llm.py,sha256=NHjm0SeQVsSIG8uISXZcQypku4QRc3KtteeO9ldv0FI,2611
 evalscope/backend/rag_eval/utils/tools.py,sha256=FU7tNu-8y8V_o_kArFVTTLM_GzL12KBNeXiwQw5SpJA,1529
 evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4tycyy-FJgzLdjeY,84
 evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=sUYvQxCtPl6CrcwhQpY8lJjW5skqWc-fvHUSnXd_MvQ,6054
 evalscope/benchmarks/__init__.py,sha256=5AXNhhmbaBFEe3u7y5TtIrviYzFI-hC8oKqxFILs1pE,937
 evalscope/benchmarks/benchmark.py,sha256=a_7Ctz36McuTyBSTYi56jis9pvOdWhg7JVSPFrbxqR4,2535
-evalscope/benchmarks/data_adapter.py,sha256=mWdxtHbordS577NqZUQZmIjlewjGDlStqc-iDvqpAyU,18061
-evalscope/benchmarks/utils.py,sha256=yXQyszzrILNiBuUrbB1BtgotQSaNA8w6X935AL1dNAw,1074
+evalscope/benchmarks/data_adapter.py,sha256=lcBoXhI1Byn0HcwbVxmIeUFxZlz_wiqte6RDPOR8sbM,18184
+evalscope/benchmarks/utils.py,sha256=jB9w3mN1eOur6j2kpQB_XZJ912fhzC0GaSeHOoylK7M,1087
 evalscope/benchmarks/aigc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aigc/t2i/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aigc/t2i/base.py,sha256=4GFAvceT1Gpt5teDLRCZi62RwvPazuhG3zwft3gN3X4,2102
 evalscope/benchmarks/aigc/t2i/evalmuse_adapter.py,sha256=WV9w3z8TxWNzVzn9A_g0xqeHh76ydnHL5xLwyg63VmU,2992
 evalscope/benchmarks/aigc/t2i/genai_bench_adapter.py,sha256=baDGFRpVcSKpc1CdzNAMBtjeCZDUpyEc5l1KyrPNoEU,1892
-evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py,sha256=But2hcQU3X3v58poF8Qg2agrxTAP6gnjZYJs8Tr0g_4,2047
+evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py,sha256=t9h5qlo4KrHOgXIhHo3z6fEAi0HfUqDZvaItQdS7dZ4,2097
 evalscope/benchmarks/aigc/t2i/hpdv2_adapter.py,sha256=U0RKN3apyD3YyZfIvqgO8TNuDO-zctlftHsSfBRyQxU,1825
 evalscope/benchmarks/aigc/t2i/tifa_adapter.py,sha256=vOOiOe26H2dk9VN2WbB_Oi3lzavMIaYDBq6sqeSIiAU,1093
 evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aime/aime24_adapter.py,sha256=GrIxCHpUwgUy8tXGTB7iQOt8k7wG8MJB0CWbwBmIy-8,1703
 evalscope/benchmarks/aime/aime25_adapter.py,sha256=yxo5roCb8ryX9ROUU2FdZ-WBTUPZ14MrBzEL0zPOh-U,1718
 evalscope/benchmarks/alpaca_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=em1YM2PxnJ8Of7Li3eqrw8PtwfeXSinfVIr-CIKVb60,4026
+evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=oUHpWrt5Gx0jF80RBd7zTh_1AWI66YvDd6U1vOMoqj0,3828
 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=0h-eT4BBmUJQrakKMPUNE1nSRwK6LHB-cflWpWzY978,6364
@@ -110,7 +110,7 @@ evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTP
 evalscope/benchmarks/ceval/ceval_adapter.py,sha256=1ITBXI0f01Dt1p7sb2RGswIeg9685Bkk2S2xmA1vat8,11295
 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=zY8dfvrTeCHAQ3d7AM02CexZw5CVKH51ZOhtT7Q1Gko,8031
+evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=Q6ncuLrCUrrhhljIfMsgWnyhHfcWWwh8iA6NZvz3W28,8079
 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=r9zael_Y2Jso0ashevYpF8e5SHOBh8iMcPIJU5WT3pQ,10367
@@ -120,10 +120,13 @@ evalscope/benchmarks/competition_math/competition_math.py,sha256=Cehyokift7oDKjc
 evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=wgejW-_QswtT8_3JKAQ_H6svH8IotDJDBEH7X4nP4bY,6760
 evalscope/benchmarks/data_collection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=QgLgIrjD3q53T-lu1UWTV6T4h1cKGoCQDh0O4QxFezw,2569
+evalscope/benchmarks/drop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/drop/drop_adapter.py,sha256=V-Vx6g2_1kcDUDWOKVX1vPSLt5iHn8NQkpWbsIwPaa4,8325
+evalscope/benchmarks/drop/utils.py,sha256=Z9PHrNnRfGqFHCLONg5SWKARp1eTJlHFc_bU46t_YrM,1344
 evalscope/benchmarks/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=fqbt61owPP7t2H4B2zbYVZTs0VBGuXNvWGvkukwhRYc,5039
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=8d5znAcQmFSmvyKV-JuMQzbY5k6xDNQQdrWZ7zgPTK4,4603
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=40mZovspVf-OXcuEu3ei6G_HZlYA8whAHSESHPPONxA,4750
 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=UB287DtnbkSQXZsbReFJqmQRwbo672DTCeXXilR_-Vc,4790
@@ -174,12 +177,15 @@ evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO
 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=to4kSKc29BmtG4q9R2PeM-sdHiL8toSyoVi1D9WMRKk,8949
+evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=TD7hkMLGZ4GK7wD7cwqJ3jCcTAaixOakUy3o5DaPYHI,8997
 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/tool_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/tool_bench/tool_bench_adapter.py,sha256=l2dBcJ4Z3m-8QFtfyFH4IqMtvkY3Rfk021P9Ff_lXWQ,2270
+evalscope/benchmarks/tool_bench/utils.py,sha256=vIPsL8FmMF2JZRHCZeLS_dDeATKNRvZDbq6T-Znlk8Q,7025
 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
@@ -187,6 +193,8 @@ evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=7tMc8vVZdBnks5jWrBSrb
 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=ueUU860kg5_xf_MtUCa6ck-fGHX3ttw8Xh3mWSJyOZA,12617
+evalscope/benchmarks/winogrande/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/winogrande/winogrande_adapter.py,sha256=UdANz3YmCtV2YfGuEihTe3vpUTlIxeXBhIqGkKbTFdU,1956
 evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
 evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
@@ -195,22 +203,22 @@ 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=Ll-qLet04aEp1WxoCKAuvZVWEZuy1lS_D-vZIN3zSQQ,13425
+evalscope/collections/evaluator.py,sha256=3sz_bL0HMFkxq3C-4P6rNGrnQolifVISI5sEpT3Bt90,15754
 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=M1JrsoZZ5OvcZfzgLrNSMtbbz5gvvCd0GwJArJQV0lk,19797
+evalscope/evaluator/evaluator.py,sha256=QzTFXiv_WdPpWTB3PgBNIz9KS_Rxu-fWDvoUpML23aA,21651
 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=5WRYuXFTDgVmolrOdiTysk-mXrpw6Qg87-iuY-VD1W4,16618
 evalscope/metrics/__init__.py,sha256=y1sdj5FBKYW1q5kLC6QREzoITHwstJRUdji6p0X5aAE,1363
-evalscope/metrics/llm_judge.py,sha256=MjyTC-xiSThk8Rd4IdUbsCXeeikoOORv6wt8H7SW8s4,4008
+evalscope/metrics/llm_judge.py,sha256=qYHsoBz-zXjL57Czl9CaPcyJT5SZr05giv5Q9SFK3cY,4000
 evalscope/metrics/math_parser.py,sha256=uTDudn305G3b8-GboWTrDE6OfrEwAW-areHnoGXZ6Is,17302
 evalscope/metrics/metrics.py,sha256=_YI7RhxlFu_JOgeE3LF9UKu6mJruvyu4FgqVf78Bjb8,13813
 evalscope/metrics/named_metrics.py,sha256=PrzU_1mGTeRFxVJFT1aXxIOiS7MnNoWyZsb8uCRVDeE,2278
-evalscope/metrics/rouge_metric.py,sha256=zhIUqenSuxnORR9tamLQBGjFwP91Zei2UiLtcOyseVM,4639
+evalscope/metrics/rouge_metric.py,sha256=bqvSotuDdC0MEKmt8v6y6tBTBx0S3Ma-tfF-cMCckA4,4645
 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/bundled_rouge_score/rouge_scorer.py,sha256=m7v8ZysO9zCuyThEoGTe5QNVt2GsKMgZpH6du1FQCvg,12110
 evalscope/metrics/t2v_metrics/__init__.py,sha256=GBxgKTPVy_qhW_F3M4Oi6QMWhdAi4PqGX5w3t6Tueho,1783
 evalscope/metrics/t2v_metrics/clipscore.py,sha256=IsrYKIlFb04-FfBq4MbSv4diS6706J15Y3G4qEFIwfU,455
 evalscope/metrics/t2v_metrics/constants.py,sha256=oY5l5fOFl8qylah9eeebZm0pgY1PYmHDa7JlUC8Qls0,451
@@ -318,19 +326,19 @@ evalscope/models/model.py,sha256=MxvJAUNkuT7IA3bchnmJDur_YCKj9ShOD2Uq40dBcGc,630
 evalscope/models/register.py,sha256=pNC69YUvw-lodYpOXmByHm26h4m0Lofgd_om-JhOBq4,1882
 evalscope/models/adapters/__init__.py,sha256=mduiDZ6LgmkefNf4CtObZk6heOB93HxxgqTuYvrqWoo,590
 evalscope/models/adapters/base_adapter.py,sha256=f2FY8DLERudkfb4_anxNVFE_D19xCJj9BObiHWspewI,3268
-evalscope/models/adapters/chat_adapter.py,sha256=HD1jAKlAv5KRjzB0s21E4rTEIhryZhZHMpSctF9xrN8,7306
+evalscope/models/adapters/chat_adapter.py,sha256=PAClyBL_nQ1I1kmjeeZ3sdC-y5ZmfFj8rjCigh_vr40,7885
 evalscope/models/adapters/choice_adapter.py,sha256=4fuz3MFEqK8ln4mMs3goMCdRPBwYmmgN70HTdr_sW_U,8005
 evalscope/models/adapters/custom_adapter.py,sha256=w8cD0b3xgcdhSZelcat67CGJnALOfz5IALzURnLjab8,2275
-evalscope/models/adapters/server_adapter.py,sha256=5kH1yDAjETogR7aOdnCEueYE1bREI40OdXdBiJpMdIM,6734
+evalscope/models/adapters/server_adapter.py,sha256=d-0ne7ymWXmvKf_ypJ0093RNwplZJwhvU2xRwc8rt70,6581
 evalscope/models/adapters/t2i_adapter.py,sha256=xkMRyZ61yTiJfmULK-p9du4nNox41pkHiV2CTFBO3qM,2659
 evalscope/models/custom/__init__.py,sha256=MZylegALg1HerOYtp-qbzu4Wb6PW3JbrxwONHU-PAVs,131
 evalscope/models/custom/custom_model.py,sha256=rBQLAuPEw_OPUtRSCEmxEfpcA8jPj8bAdsmtKs4ygus,1566
 evalscope/models/custom/dummy_model.py,sha256=WRT_aCBZLXnC4yRCgggkuySkhM71C47O2Txx_YNc3UM,1933
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/arguments.py,sha256=UZKlkbDE2N408dY8Ji-WB8sl1rcmamywzxLvNXpnY0w,10194
-evalscope/perf/benchmark.py,sha256=nv7gtCkeKnLKQQiKM4G0MYO2ambcuwsbx67OgEQG0nM,7917
+evalscope/perf/arguments.py,sha256=5dTtaBR9BIobaKkX1Xj-mphHDG4uugnGaVOvWpLfN04,10714
+evalscope/perf/benchmark.py,sha256=eGnxMLQXSYBGRJS4tS8geSJAirnuWo35M4orlRZzei8,7847
 evalscope/perf/http_client.py,sha256=-c3-N7bxKsj3d5DVsKSaYA3XAHJDzZgoqZBbhuDYIGk,7419
-evalscope/perf/main.py,sha256=w-yDbl0osaTAMgC-JNPpqIq2LQ7U4c-Ht7Amj8Nbjc8,1278
+evalscope/perf/main.py,sha256=clHzkQNmv7wv-OWkuNGDQ-8YoLUCWxARIX-Eisinpms,3096
 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
@@ -349,11 +357,12 @@ evalscope/perf/plugin/datasets/random_dataset.py,sha256=SIlsjAE_Stknfr6o1CBFvANB
 evalscope/perf/plugin/datasets/speed_benchmark.py,sha256=J6q7AF_Re5eHLVejXEw9c1jlk1T1PPmist0yO9UFTPE,2432
 evalscope/perf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/perf/utils/analysis_result.py,sha256=ESzaZHGTpr2LoJR3jpOzqMphxSrr79d364ZzD159PmY,1169
-evalscope/perf/utils/benchmark_util.py,sha256=CftjnxYA7d1aeAL_iuyXcJPwCL5A8zWGZSkNtjrMyW8,6309
-evalscope/perf/utils/db_util.py,sha256=efz6qQtMIYAIpG0sAEjLwuzTHBUiuzAV1n7_DCGrN5o,9461
+evalscope/perf/utils/benchmark_util.py,sha256=PcRTeKlEIslBw0zKVS2mFg6GgJ6J8m1f2-gAaEBeiHI,7236
+evalscope/perf/utils/db_util.py,sha256=xqrXZapP_WwUdzkgFBTh3LDBWzr_UoU8v13rOjQ8TT4,9876
 evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
 evalscope/perf/utils/local_server.py,sha256=clF8i0UFmaxBBB6gX05KvVCyzSv0xzsAidz0_sLLlAk,4627
-evalscope/perf/utils/log_utils.py,sha256=1jmB31W3ol9ukPAPbQ8xG3yoZ9oi3tjEyMK5M3ERmbw,1471
+evalscope/perf/utils/log_utils.py,sha256=Xm5A8g8BaozaI_0TaPzr2aAxUBCCf-w7II-FcifrIYg,1503
+evalscope/perf/utils/rich_display.py,sha256=SavP2L44UwN58ZUGR2W1wxM4h4F1iyPa90HhT-Ypkzs,8125
 evalscope/registry/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/registry/config/cfg_arena.yaml,sha256=rub6ceaQxxB1mbSjdoFf0IaVgGfbOonV2nYRebv2OKo,3292
 evalscope/registry/config/cfg_arena_zhihu.yaml,sha256=tvvihBwvoTjoezwTSaZwoGOB44ysofpnin4pNyY9TfQ,2755
@@ -376,11 +385,11 @@ 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=iLNqx7CnHSHQmOBqWUK_vt2VIjnvGslJTqn--7B4y_s,316
-evalscope/report/app.py,sha256=8pcQi5oYAYa9hXoMoMUNfy9jSvSR9DDiXyLcyPd9AmA,28459
+evalscope/report/app.py,sha256=FxNpiEmbpH_B7D5SYN42idGsyOgkgFrLzScOVrwL3SI,28998
 evalscope/report/app_arguments.py,sha256=1wHTLeFx1G94cKXYOeOVe_wTiOY2D929UctIRGOtRaQ,699
 evalscope/report/combinator.py,sha256=O3QirwtYhDhdaWVT4STJMCGZMwoX8BTeJ3HtS9iwnWQ,2567
 evalscope/report/generator.py,sha256=q9aHWNjQgvutAKtpjfWOpfu5zNFdnXilO9OqBqt_Phg,3612
-evalscope/report/utils.py,sha256=DRlbjbqHEmM8rGlA4pwtlHFhOZtyUzcqiS-mejfIDkU,4584
+evalscope/report/utils.py,sha256=uu-rAzoN6ZIlv52IDWSZCcmNVY3DscNo2f9H9-gjZHY,4602
 evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/third_party/longbench_write/README.md,sha256=1yLKeSVIcihpoc4KXr8NpK86JbcLssCPx76aOKdPbYI,5431
 evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u7z6OI79czoBlP8lX4PVo,126
@@ -413,13 +422,14 @@ evalscope/third_party/toolbench_static/config_default.yaml,sha256=-6n6Zyg9eHN2ee
 evalscope/third_party/toolbench_static/eval.py,sha256=do_-lVi_vEoljeLYvt3b_AYSMqpdKzgYnTek9WLSKe8,8236
 evalscope/third_party/toolbench_static/infer.py,sha256=rsADLhEd2IBcC6EI9aD7hSJmo6Oo5b22mnHWBCZLDPs,9010
 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/toolbench_static.py,sha256=xE__eXvSwHmmSh1tXNvyBo6MCO4mDlYTbIYl9OGEfNI,2120
 evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 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=U2jtrkOa2asRp16Zam0zIi_38mCyWQqql_L6JSwii4I,8749
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
+evalscope/utils/deprecation_utils.py,sha256=WyeiLWSi5ti6FkuMbhimcPPUB43paa1FZ5-JOAWNFZI,1344
 evalscope/utils/filters.py,sha256=x_NX40uWMmUsVrAGHCeeV2e63HZZFugWUgdUhk64ivM,1523
 evalscope/utils/import_utils.py,sha256=Oo8saX_mMw4U1RrA7_pn8FmV6P9laru4fEgecqqwpqk,2585
 evalscope/utils/io_utils.py,sha256=Tjdgen1FsAA4ArqiUzu734L0Px5NuiS0GKRRiGIzxSA,4192
@@ -429,13 +439,13 @@ evalscope/utils/utils.py,sha256=hP_ntROFsZ-zaNVpJtT2prNo8iX-UAKfRtdxbLtPJng,1110
 tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
 tests/aigc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/aigc/test_t2i.py,sha256=_M3WxY5ruBM4RD7rYHhgizcIhH-ny5XD9M16Ayl3UPk,2619
+tests/aigc/test_t2i.py,sha256=BcdS3OMypWnraXF4Cq3DhDVRpZq0qo9_0Qpyg54B7FY,2627
 tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/cli/test_all.py,sha256=pwup--iNxckUEsR_aFjIAbEQo3UogSu5aIWf9ryLP2o,4022
-tests/cli/test_collection.py,sha256=y8FjoPziPRf5BdJK8DHjcXn26ETKz1OyqjnCpwjt-F4,4096
-tests/cli/test_run.py,sha256=4B-6sOyotK3omirZWWyg7-CcnUSeZjiaU3aXHr0hH_Y,16804
+tests/cli/test_all.py,sha256=O3lXwOV7A0f0rmltofrjpphnshjNtaZC6NUPG-wsQjg,4082
+tests/cli/test_collection.py,sha256=_11mSCWLaiCgheA3uguv6uI3CxqaHUKVwzS6T5BGmxs,4145
+tests/cli/test_run.py,sha256=FTFiAb8Ge5raB1aa0Nzw8DPjFLyAlLfXHRQVIWjvvGE,17798
 tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=8K5tGlWwOpYWnJ0GaCpqSw9zPOiM8fEKJaDil2mpTSQ,3831
+tests/perf/test_perf.py,sha256=VbXsqiqgQY3R3bVKizYQmP04UPluUS26MO6YhTzMs48,4848
 tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/rag/test_clip_benchmark.py,sha256=ZCBtgnF8Vuji6WQlb92-_RIvXlUX_Xt-cHZP4AN_DNI,2552
 tests/rag/test_mteb.py,sha256=YJw6X1jwX6SYNB-ryVb-OHJWu3vsE3Y4STATI75rdG0,5619
@@ -446,9 +456,9 @@ 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=UqRiBPMU3vRtLIG1Qu4ZVhyUQx-zGYQuLCgobwf-7a4,3176
-evalscope-0.15.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.15.0.dist-info/METADATA,sha256=MLn0s_L7s0oeQPWL1XuhihDAFJnzLdVTvdrep-9Bgag,34053
-evalscope-0.15.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.15.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.15.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.15.0.dist-info/RECORD,,
+evalscope-0.16.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-0.16.0.dist-info/METADATA,sha256=zX2L_cLxOjX-NNbiR40dmPOxUWyOH86zJycYjr4j5Po,35492
+evalscope-0.16.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-0.16.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.16.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-0.16.0.dist-info/RECORD,,

tests/aigc/test_t2i.py

@@ -59,9 +59,9 @@ class TestRun(unittest.TestCase):
             },
             datasets=[
                 'tifa160',
-                'genai_bench',
-                'evalmuse',
-                'hpdv2',
+                # 'genai_bench',
+                # 'evalmuse',
+                # 'hpdv2',
             ],
             dataset_args={
                 'tifa160': {
@@ -81,7 +81,7 @@ class TestRun(unittest.TestCase):
                 'num_inference_steps': 50,
                 'guidance_scale': 7.5
             },
-            use_cache='outputs/20250427_134122',
+            # use_cache='outputs/20250427_134122',
         )
 
         run_task(task_cfg=task_cfg)

tests/cli/test_all.py

@@ -46,6 +46,9 @@ datasets=[
         'alpaca_eval',
         'arena_hard',
         'maritime_bench',
+        'drop',
+        'winogrande',
+        'tool_bench',
 ]
 
 dataset_args={

tests/cli/test_collection.py

@@ -78,7 +78,8 @@ class TestCollection(unittest.TestCase):
                 'model_id': 'qwen2.5-7b-instruct',
                 'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
                 'api_key': os.getenv('DASHSCOPE_API_KEY'),
-            }
+            },
+            use_cache='outputs/20250519_114427'
         )
         res = run_task(task_cfg=task_cfg)
         print(res)

tests/cli/test_run.py

@@ -73,6 +73,12 @@ class TestRun(unittest.TestCase):
         logger.info(f'>>test_run_eval_with_args stdout: {run_res.stdout}')
         logger.error(f'>>test_run_eval_with_args stderr: {run_res.stderr}')
 
+    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
+    def test_run_yaml_config(self):
+        from evalscope import run_task
+
+        run_task(task_cfg='examples/tasks/eval_native.yaml')
+
     @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
     def test_run_task(self):
         task_cfg = TaskConfig(
@@ -207,14 +213,18 @@ class TestRun(unittest.TestCase):
         from evalscope.config import TaskConfig
 
         task_cfg = TaskConfig(
-            model='Qwen/Qwen2.5-0.5B-Instruct',
+            model='Qwen/Qwen3-1.7B',
             datasets=[
-                # 'iquiz',
+                'iquiz',
                 # 'math_500',
                 # 'aime24',
                 # 'competition_math',
-                'mmlu',
+                # 'mmlu',
+                # 'simple_qa',
             ],
+            model_args={
+                'device_map': 'auto',
+            },
             dataset_args={
                 'competition_math': {
                     'subset_list': ['Level 4', 'Level 5']
@@ -224,8 +234,16 @@ class TestRun(unittest.TestCase):
                     'few_shot_num': 0
                 },
             },
-            limit=10,
-            eval_batch_size=10,
+            limit=5,
+            eval_batch_size=5,
+            generation_config={
+                'max_new_tokens': 1000,  # 最大生成token数，建议设置为较大值避免输出截断
+                'temperature': 0.7,  # 采样温度 (qwen 报告推荐值)
+                'top_p': 0.8,  # top-p采样 (qwen 报告推荐值)
+                'top_k': 20,  # top-k采样 (qwen 报告推荐值)
+                'chat_template_kwargs': {'enable_thinking': False}  # 关闭思考模式
+            },
+            judge_strategy=JudgeStrategy.AUTO,
         )
 
         run_task(task_cfg=task_cfg)
@@ -269,7 +287,7 @@ class TestRun(unittest.TestCase):
             datasets=[
                 # 'iquiz',
                 # 'ifeval',
-                'mmlu',
+                # 'mmlu',
                 # 'mmlu_pro',
                 # 'musr',
                 # 'process_bench',
@@ -287,10 +305,13 @@ class TestRun(unittest.TestCase):
                 # 'ceval',
                 # 'hellaswag',
                 # 'general_mcq',
-                # 'general_qa'
+                # 'general_qa',
                 # 'super_gpqa',
                 # 'mmlu_redux',
-                # 'maritime_bench'
+                # 'maritime_bench',
+                # 'drop',
+                # 'winogrande',
+                'tool_bench',
             ],
             dataset_args={
                 'mmlu': {
@@ -356,14 +377,16 @@ class TestRun(unittest.TestCase):
                 },
             },
             eval_batch_size=32,
-            limit=15,
+            limit=10,
             debug=True,
             stream=False,
             generation_config={
                 'temperature': 0,
                 'n': 1,
                 'max_tokens': 4096,
-            }
+            },
+            # ignore_errors=True,
+            use_cache='outputs/20250519_142106'
         )
 
         run_task(task_cfg=task_cfg)
@@ -416,12 +439,12 @@ class TestRun(unittest.TestCase):
                 # 'gsm8k'
                 # 'truthful_qa',
                 # 'simple_qa',
-                # 'chinese_simpleqa',
+                'chinese_simpleqa',
                 # 'live_code_bench',
                 # 'humaneval',
                 # 'general_qa',
                 # 'alpaca_eval',
-                'arena_hard'
+                # 'arena_hard'
             ],
             dataset_args={
                 'competition_math': {
@@ -447,7 +470,7 @@ class TestRun(unittest.TestCase):
                     ]
                 },
             },
-            eval_batch_size=5,
+            eval_batch_size=10,
             limit=10,
             judge_strategy=JudgeStrategy.AUTO,
             judge_worker_num=5,
@@ -468,7 +491,7 @@ class TestRun(unittest.TestCase):
             },
             timeout=60000,
             stream=True,
-            # use_cache='outputs/20250320_143658'
+            use_cache='outputs/20250519_142551'
         )
 
         run_task(task_cfg=task_cfg)

tests/perf/test_perf.py

@@ -103,7 +103,7 @@ class TestPerf(unittest.TestCase):
         from evalscope.perf.arguments import Arguments
         task_cfg = Arguments(
             parallel=20,
-            model='Qwen2.5-0.5B-Instruct',
+            model='Qwen3-1.7B',
             url='http://127.0.0.1:8801/v1/completions',
             api='openai',
             dataset='random',
@@ -117,8 +117,33 @@ class TestPerf(unittest.TestCase):
             seed=None,
             extra_args={'ignore_eos': True}
         )
-        run_perf_benchmark(task_cfg)
+        metrics_result, percentile_result = run_perf_benchmark(task_cfg)
+        print(metrics_result)
+        print(percentile_result)
 
+    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
+    def test_run_perf_multi_parallel(self):
+        from evalscope.perf.arguments import Arguments
+        task_cfg = Arguments(
+            parallel=[1, 2],
+            number=[2, 5],
+            model='qwen2.5-7b-instruct',
+            url='https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions',
+            api_key=env.get('DASHSCOPE_API_KEY'),
+            api='openai',
+            dataset='random',
+            min_tokens=100,
+            max_tokens=100,
+            prefix_length=0,
+            min_prompt_length=1024,
+            max_prompt_length=1024,
+            tokenizer_path='Qwen/Qwen2.5-0.5B-Instruct',
+            seed=None,
+            extra_args={'ignore_eos': True}
+        )
+        metrics_result, percentile_result = run_perf_benchmark(task_cfg)
+        print(metrics_result)
+        print(percentile_result)
 
 if __name__ == '__main__':
     unittest.main(buffer=False)