evalscope 1.0.1__py3-none-any.whl → 1.0.2__py3-none-any.whl

{evalscope-1.0.1.dist-info → evalscope-1.0.2.dist-info}/RECORD

@@ -1,47 +1,48 @@
 evalscope/__init__.py,sha256=oivLvqwNw2JlB-h-Z8_525IpfKcYEkS51F59tEfpy5w,445
-evalscope/arguments.py,sha256=OthHwNhG9VrP7_CYocmjZ4iVyG5LJbzO0FhseoLBalk,5663
-evalscope/config.py,sha256=NVFXbU0kVof2V8Bnjs-O2FEPdlXx3rZuoHcttm1THbM,10564
-evalscope/constants.py,sha256=cbkKHmEcJHF9T0m4yREx08__tulj6MV59im2RW-pR3c,3433
-evalscope/run.py,sha256=1JjqSky3Fm3v1tOE9pgR7alODoSNWa4ZdoLTWFLgjRE,6510
+evalscope/arguments.py,sha256=jKAF47PsqXRioU21gRHw9hxJnfR31z_X7c__glRY5ns,6257
+evalscope/config.py,sha256=S2N11-AxQkT7lVffpjXdtpT4QpnSP6th-c8I-501mwM,11507
+evalscope/constants.py,sha256=W3E4Jp-x6qxvPOYtU9bNlzlERFvSAA_3F007apIwUlU,3601
+evalscope/run.py,sha256=A9_7pR3FiA-It46A3Mqk7ce6fQy548p0ux2QUugj2hI,6531
 evalscope/summarizer.py,sha256=HUDJ1zKi22uNst3AUfX67Z0sHzeZy-4S8sYyvxJnBzc,5901
-evalscope/version.py,sha256=5Jk88EAyvBpPzsQaFYKGjukIwF3tVCXIrarT94bYsCQ,118
+evalscope/version.py,sha256=H_zHGJkiB6equdW6Jo4F_hhdLYKZqriowav05O5_CeY,118
 evalscope/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/api/registry.py,sha256=Qk0KMGDbt-iI0-OfoJZbOtxt76qreAVWh36HOoQAKM4,5448
 evalscope/api/benchmark/__init__.py,sha256=9xcTxpcQ6HhZ0QDwEIZhAT5IjybzaJ60VGLcmaFE5dU,188
-evalscope/api/benchmark/benchmark.py,sha256=q5hmEH845DfmvEB1NvlHM1b-oCCMpatIamT-2ubudbM,10088
-evalscope/api/benchmark/meta.py,sha256=G6Q5E1JwO-CpEwsjhMrXHExlVRUF1Ah5Nz21vkP8IV0,4218
+evalscope/api/benchmark/benchmark.py,sha256=gqAM81SeGb_Q0rA6Q-LFpnNkOUiwOj43aRWECtCxAOE,10832
+evalscope/api/benchmark/meta.py,sha256=N4u8NQjkjIw-xaf6KFnb6C8JDKB0DLbsXyXblDqIpvE,4304
 evalscope/api/benchmark/adapters/__init__.py,sha256=uLt_GiU4s-_6Rjgmr4OUTtE7dvEX-ZIQ403fd6oNuxA,264
-evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=Y8wzOxq3qpbE2lgLZyXHxoLUxjlmbS-N6ByObrBwOvc,27977
+evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=WS4Pm0pk51Se196Ho31FmOqGyOajTtUGbbjWD9U7UwU,28064
 evalscope/api/benchmark/adapters/image_edit_adapter.py,sha256=06V-_A8RKuMNYMt7-vaXn2qBa9LIZgfFO_6PUuhAkh0,3052
-evalscope/api/benchmark/adapters/multi_choice_adapter.py,sha256=wp_6Kws3GoBk_mSzQP8Nr40osFf3iPJpntkANYAuIcc,2979
-evalscope/api/benchmark/adapters/text2image_adapter.py,sha256=4mccYHKB-9iyOZ0uwkTi2TgC76KIJpcu_4hnfbU5NMc,6434
-evalscope/api/benchmark/adapters/vision_language_adapter.py,sha256=N9LPh5tTGkvRYzp4giI0La0u4xzrHcJGhdTY9jiNCxY,219
+evalscope/api/benchmark/adapters/multi_choice_adapter.py,sha256=auqLNvF50Or9bo3LOmQLXHfFaTTCTqvQzZog3glInng,3062
+evalscope/api/benchmark/adapters/text2image_adapter.py,sha256=jO64hwjQexIv-MTyHH0Ffp_6p--9TKufOmX_U39mAnE,6385
+evalscope/api/benchmark/adapters/vision_language_adapter.py,sha256=5d7ITkeosikb7u0ag0WkMaZ0SAYGkR_wKM9NP495GKk,280
 evalscope/api/dataset/__init__.py,sha256=RHFMzwfONEqmmn3vRtxyN3r29mipDUUUSEDhuwm0YpQ,147
 evalscope/api/dataset/dataset.py,sha256=9bwSx89zgOOBRQkRPVv-B5Yi30A6J1MLtekQSqwsy9g,11328
 evalscope/api/dataset/loader.py,sha256=t7KLH5ltLUumhiPIyYJzk6zn2iKLx-D2gIIoMhKdnhc,9714
 evalscope/api/dataset/utils.py,sha256=3E0ikqr6QWV_lX0d3Z4F4xFuVTcwbeDPgCvJY7v83Bc,4935
 evalscope/api/evaluator/__init__.py,sha256=-Ure6X4GlE7VYSNWSZ_DpjbUBGa5irVTymLENEHTYqY,138
 evalscope/api/evaluator/cache.py,sha256=a_M2ouUjtkMr5m3wRbmsE8ETP_aacxbm0d38yY5RljM,13244
-evalscope/api/evaluator/evaluator.py,sha256=SGW4RIKc79IlUP5FisrEycJlqORcaYxyIP5eabaSfeU,1600
-evalscope/api/evaluator/state.py,sha256=OyZUtQw9Wd6X8MA2mtmTGn74ReBq1x-JfWwV_TT99UY,8892
+evalscope/api/evaluator/evaluator.py,sha256=xMF4w2qiQ7NNgOhSKs9Vd4VZ33SCDwTTJ82lDhaj1FQ,1734
+evalscope/api/evaluator/state.py,sha256=Elz2cmbvOOqvOaEOAMatxgk4BdjqDZB3XKTaL4iqJLI,9039
 evalscope/api/filter/__init__.py,sha256=5eWKjT-dAiz8nE0S6WnU6plqjXZHYn7CJOgFiHSoovM,66
 evalscope/api/filter/filter.py,sha256=fsPddaHE5wwFIXgUWITFqlYXqdh6vx3QqcEf3rSXKVI,2068
 evalscope/api/messages/__init__.py,sha256=UKZ9VVCt7NPrcZXv_1e8MZ8mOWu0eLRvMIXykpJPZ9I,378
-evalscope/api/messages/chat_message.py,sha256=LZ3Yv_Ts5ASCfrq2y_zecpY3IN5lzHsRbaxz8WRQgD8,9698
+evalscope/api/messages/chat_message.py,sha256=D88TklSAWOaG21EBDVDoRPwzVCqzEGbVW4sA8Af4axc,10053
 evalscope/api/messages/content.py,sha256=gUBUeK60BUhkwoulyzKL6q0iMt3VLlah9onLG1XVrWY,2772
 evalscope/api/messages/utils.py,sha256=uqlEbYEoUKpXLW8tQtP-cY5Miq7W0Xl6a98j55u6m6E,1266
 evalscope/api/metric/__init__.py,sha256=Cj2F8eiVny5uNtfPXKwQDq2owlHVKNzfr-COLYMEox4,106
 evalscope/api/metric/metric.py,sha256=XkjBqpZbFYynhTIH8WawfPmItbDQ6jWufE_ox9zDPCU,1568
 evalscope/api/metric/scorer.py,sha256=dczSQwkRmPk1uvNCMGT5G6nYbwWTcpwsZtyYXWkrJII,3749
-evalscope/api/mixin/__init__.py,sha256=DpHdR7t9d-HUzBXxwsW3t5MxM4kgoThQ4WF8s8EuSBY,43
-evalscope/api/mixin/llm_judge_mixin.py,sha256=KPNH41IL7md5XEYqC2ZbmnYm4tIrV-MgxpfKOWbYsMc,5624
+evalscope/api/mixin/__init__.py,sha256=xBuoTuao5o_EFThgeeeWI87x64Q12aJttsaZc8gak_c,83
+evalscope/api/mixin/llm_judge_mixin.py,sha256=ECVDfxCeAEkymFssD7xKhIDcct2qgQTqGnbijXk9leE,5675
+evalscope/api/mixin/sandbox_mixin.py,sha256=uKqBtTtttKwrUArY-CTMDdFHjRBOR7Kl1sxaGHe-S2Q,7653
 evalscope/api/model/__init__.py,sha256=YxKdz1IKUt6eYoC7nx81yD2BtyiWQDvaoTcc8O9lvoE,286
-evalscope/api/model/generate_config.py,sha256=SyUNlZhcoBpLlMK8esu1XQs61SSPN_D5QN8TRUcnroI,7760
-evalscope/api/model/model.py,sha256=HecfGqaaB201n7I1pZ5Q4_aVC-xLA93uxdGgoreRYFw,12771
+evalscope/api/model/generate_config.py,sha256=wQeDknXb49yBKSRL9rlIyerPobGXqU-A4hL1vySNGPo,7656
+evalscope/api/model/model.py,sha256=c7YVbYYk47MHWwPjoB66xWjgmHdUGTOSOdtIsLcJfyc,12782
 evalscope/api/model/model_output.py,sha256=NeN6bLtAvg_3fTirewWfdP-_x4SJXa9pGuRpyXJY3B8,9333
 evalscope/api/tool/__init__.py,sha256=bEaW5ryY-erLcl2zMoDJNgiaBqlSPAL0jQ5daUHvvrw,272
 evalscope/api/tool/tool_call.py,sha256=WqMnw69L_yhQWycENZ7azPRhxRidhmrMcYAy7UTIqvg,2836
-evalscope/api/tool/tool_info.py,sha256=aqquWQRWWx7fPItIwiubiz2VRe2TLl_Jmn1ArIlngbw,5716
+evalscope/api/tool/tool_info.py,sha256=FQOBqxKZ6Qb4f40iRH1mLg64cEhu1_-9Rn-f5iUrD2w,5733
 evalscope/api/tool/utils.py,sha256=IWFzM6WspzBmNPicXn6b7KS6Y-1I-ErsK9fua4cb53Y,2324
 evalscope/app/__init__.py,sha256=HWLXld_JXcBDsdL4L_4E8JsKyuBwwPUSwlejKnZ3HKc,579
 evalscope/app/app.py,sha256=EaBWorA87ZmyIHovIE3styHWEVFsu_F70pTmP4-5zTQ,836
@@ -107,18 +108,22 @@ evalscope/backend/rag_eval/utils/tools.py,sha256=FU7tNu-8y8V_o_kArFVTTLM_GzL12KB
 evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4tycyy-FJgzLdjeY,84
 evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=jlwM13Ty-Ax6AeMsNlo9xIBupNFgnceYuXtCmh0hNTQ,6160
 evalscope/benchmarks/__init__.py,sha256=WHR4ej9Tqa2N9CyIaUWXS8EnHZtcujaNeg9hf8GT31Y,1182
+evalscope/benchmarks/ai2d/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/ai2d/ai2d_adapter.py,sha256=3GBNV4cNv9bBLJRdG_uA9qNhuN6qAEutHl8d-rsFpFU,2018
 evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aime/aime24_adapter.py,sha256=HTlriHoHzlm1Rf3KAiGRLs8sx6Gyf6s7RGtOjk_hGS4,1767
 evalscope/benchmarks/aime/aime25_adapter.py,sha256=ZOE_6Zhg1MatWJSu2Zq372nKUODYtNFZimS1MJRFz5A,1591
 evalscope/benchmarks/alpaca_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=sjaWcK8WH1XY0kzm5eHsq_7J62EJocAf4gRV_UB8ZBE,4971
+evalscope/benchmarks/amc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/amc/amc_adapter.py,sha256=NzLPOmj3fJhPw6gVrB8KtxEbqwUqQ923vXHnLWEfdiU,1418
 evalscope/benchmarks/arc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/arc/arc_adapter.py,sha256=GASZmoJ-PpzBG70cBdABZA5uVqoyosjV-jf9WShK7L8,1622
 evalscope/benchmarks/arena_hard/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/arena_hard/arena_hard_adapter.py,sha256=Ddn_hVO1PvNQ_kNknXfdJCz1AVnXZEdGWq4gX1_Qqow,7275
 evalscope/benchmarks/arena_hard/utils.py,sha256=23xCd7_ksrM4xMJBp7N2ZwpUpq1zpoQFjLm1oBcdgQY,5559
 evalscope/benchmarks/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/bbh/bbh_adapter.py,sha256=GcvgwBhIw7OG-ljWQ_urVOoWlrFjrBy1LAZ-Atm02Dw,5570
+evalscope/benchmarks/bbh/bbh_adapter.py,sha256=lRI-DfdFkyg4ylW4d-6CUfiNqlF7K_IoTjzJz3jYTUs,6346
 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
@@ -147,8 +152,8 @@ 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/bfcl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/bfcl/bfcl_adapter.py,sha256=N_AVgdfI4DXph0n3U1bChP9AQLx3_-ogAInFE-4EGig,10972
-evalscope/benchmarks/bfcl/generation.py,sha256=gOYzwTNEi2G0zykKdsx42Pc0Ql8iPD6RoX3MRbUhMJo,8698
+evalscope/benchmarks/bfcl/bfcl_adapter.py,sha256=WzpL7XWDdx-EvbLluIOiMlADTO42CYs0IwQFvIfhTI0,18402
+evalscope/benchmarks/bfcl/generation.py,sha256=c6lNjo-VTSUrVg-pqyPSucrbCKBOdBSyN0aR5AAtE4A,8701
 evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/ceval/ceval_adapter.py,sha256=4FLPgY-UtqINafnNxfOsE9AwS6GFXFCUGOBI-4EZUGk,8503
 evalscope/benchmarks/chinese_simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -163,7 +168,7 @@ evalscope/benchmarks/docmath/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 evalscope/benchmarks/docmath/docmath_adapter.py,sha256=-mel6hA-x_e7fV0uOHdX5BpoQEVyQ5VqwIwEqSNDpnc,4623
 evalscope/benchmarks/docmath/utils.py,sha256=d6Yjoa5q91kjr1SdVPVBndzDaUzMlO_GfEqMtUXXr0s,7707
 evalscope/benchmarks/drop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/drop/drop_adapter.py,sha256=PyvZ1WOdHQ0u0_JpuP97_yQsCUbzGcYsJf3bWKbakzg,9968
+evalscope/benchmarks/drop/drop_adapter.py,sha256=Jbbr5O_Y5LI_vT_RskRQVKxGkiIraX_uXP7fYaZ5eZs,9995
 evalscope/benchmarks/drop/utils.py,sha256=Z9PHrNnRfGqFHCLONg5SWKARp1eTJlHFc_bU46t_YrM,1344
 evalscope/benchmarks/frames/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/frames/frames_adapter.py,sha256=w1kRya7w5omt95HHE6AzbzYVhyTT5r521676d_xJ6Vg,5514
@@ -180,12 +185,16 @@ evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=zWK2hhyKw5n8K30YvMjSm6XMwyrireO
 evalscope/benchmarks/gpqa/prompt.py,sha256=b1Gw2D5dEdhvLYymPfcvGKJdHrIzpiZkOwURKSxiQJg,5576
 evalscope/benchmarks/gsm8k/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=W4vTXsC7iHN1AgvpaCf1Rj7y2O8QczIluucnpSC5aYo,2636
+evalscope/benchmarks/healthbench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/healthbench/healthbench_adapter.py,sha256=1sL7i9yhORH4xiFWB9puPKWNZZFJGZFAlKdlzHp-fiw,13228
+evalscope/benchmarks/healthbench/utils.py,sha256=M8SnOEhlqXWm03CFE6CAtbMiu6MqdGgVczAv-LPjA7Y,3683
 evalscope/benchmarks/hellaswag/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=tAe63NfV5ljUm1f4RTSFxWOVKBUhk3Cc0EGzF5uYLK4,2041
 evalscope/benchmarks/hle/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/hle/hle_adapter.py,sha256=4YVmETL9mEiLxF4vWRjePLyFaxelax6nOaqoAH5ZxmU,6389
 evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=5x2pnkbI9ZPPOyrRBsJ5ZcOCGJr8OR7qXLgVlY6eJxs,5825
+evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=uLs3UHSALS3YHt0qzBismrIqdEUgbEalQbjC0CU7ym4,4085
+evalscope/benchmarks/humaneval/utils.py,sha256=rPnc_JuSjNg9aV7UMUwsLrDlm-ufj64GNIBCWBeuRcM,6517
 evalscope/benchmarks/ifeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=55FQwJ0_eDijppkVVlM5XCXzgRFmjH1SvGMItGsvn6o,2769
 evalscope/benchmarks/ifeval/instructions.py,sha256=HXnn1JgU3dpYltqIovFAn02DxkYOGw337kLMlOfJxJE,56048
@@ -200,19 +209,26 @@ evalscope/benchmarks/image_edit/gedit/vie_prompts.py,sha256=qVXWQyVUwZxEasDjVmYB
 evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=mNHA_Fuj_gAdOEoR7oChnGmErf1czqwnk8Zk-jRhBys,1304
 evalscope/benchmarks/live_code_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/live_code_bench/evaluate_utils.py,sha256=wgx8RDbkXi2Mlt-aK_6o4VcoPb7I3eL8z8h8JW4SnEo,6510
+evalscope/benchmarks/live_code_bench/evaluate_utils.py,sha256=maN8qHmDHJpexPeB0qwZoXJ5zrqPbJDYVRptqvXI9d4,6827
 evalscope/benchmarks/live_code_bench/extract_utils.py,sha256=ZcQ8y741uawPo6I_1_XglR3eqJFDNrqc8fILKZupVRs,2375
-evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py,sha256=tl7nGLDUgmNtyR4faE0aoW11OgLhsx7ZdKmONGDlQnQ,5203
+evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py,sha256=qnprJTv7zWA9aq6Lw4aDoall---kiivR0oDo3uSO2mI,6399
 evalscope/benchmarks/live_code_bench/load_utils.py,sha256=fEzWz_fUGwi5Ncum5PNVF9jFcuDwGgs7Vt_10YKBE2Q,2087
 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/sandbox_evaluate_utils.py,sha256=7DDx46EwtoR776vWjofJl1zaYCLdmeq8cF3fhDGdZgA,7424
 evalscope/benchmarks/live_code_bench/testing_util.py,sha256=TuoOTciC-hz3FTeDzsQB_THH3Be9UOP2XMrax-4sXkM,17282
 evalscope/benchmarks/maritime_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py,sha256=Rx7iZ5JaEo73YwIzhm78gMDQ6gqcErbnWWXHxXM6BcU,2379
 evalscope/benchmarks/math_500/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/math_500/math_500_adapter.py,sha256=uuxjmqftY_r-hJBCjfBgYUELrBaB86MG8dIu2wTikgI,1848
+evalscope/benchmarks/math_500/math_500_adapter.py,sha256=hn7SQhoIHKuH-2A_nGUhQPRw2gl2G-kZldc9ueY0G3A,1802
 evalscope/benchmarks/math_vista/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/math_vista/math_vista_adapter.py,sha256=Mu9BpH0rDNM0yMrGws4SEOnXy2NTSIKwyLs5t4nAP-s,5842
+evalscope/benchmarks/minerva_math/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/minerva_math/minerva_math_adapter.py,sha256=jyT9_D4w8PTtLBN3Kn10_CnssH_mPuRNnn9rek_zUEs,1655
+evalscope/benchmarks/mm_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/mm_bench/mm_bench_adapter.py,sha256=py0DakGQX1JE2rqYjYN9w_-H0DtQ-YqG5k2s_UzbxxU,4372
+evalscope/benchmarks/mm_star/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/mm_star/mm_star_adapter.py,sha256=oamLv6U2-JAK5mdVLkUgYxkOahxQkQYMRKAyu_xPAUE,2818
 evalscope/benchmarks/mmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=2NT3QbfPzajUTFZ0tBCl6PRrtFtAr5jPZNQRW2Idlno,5947
 evalscope/benchmarks/mmlu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -222,16 +238,27 @@ evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py,sha256=m_37OIFrJB4ZIvtbDJ_
 evalscope/benchmarks/mmmu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/mmmu/mmmu_adapter.py,sha256=C7UM6HvomcA_Srf7771S0CaUvifBX63i161XaacraGQ,6038
 evalscope/benchmarks/mmmu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py,sha256=a7rZV4WMPxeBdfwanmUjsB8yG1rwNXCsWCoqzOq-dd4,4901
+evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py,sha256=banPS1nDt9bQ95urKbSZnR-hBTw23eL9MSrHt_0ZLp0,4725
+evalscope/benchmarks/multi_if/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/multi_if/ifeval.py,sha256=7y2rnJ4q1_DVA7I9mUnF7TBpu7Kez0X_Xhl-AJInzWk,87949
+evalscope/benchmarks/multi_if/metrics.py,sha256=LWnhQw25cRNMReJ_xJ7Fx7WYHcT9i2FG1FUjYOuQDrI,4291
+evalscope/benchmarks/multi_if/multi_if_adapter.py,sha256=I3_YPPUuRbrs9Gt3Qjhx9RM5Vu2gDFnheDcGu-oe840,5924
 evalscope/benchmarks/musr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/musr/musr_adapter.py,sha256=kx6bckj7Nijl4Wysuj-mKYdy0hIRDJho8yVTup403Hc,1473
 evalscope/benchmarks/needle_haystack/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py,sha256=mO8zhdCpoWPtlBk9GSzgcP25vEoQLYGwUM1QfcQ4iSE,17151
+evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py,sha256=GYaswWPwYI3aV5HSpcuBTgW9-HDtf2xzNZg0WrsI0Yo,17033
 evalscope/benchmarks/needle_haystack/utils.py,sha256=k8WDigqt5LgzHw6DtaYsLtb3BJL0FTZS9JOyJCpoPq8,2935
+evalscope/benchmarks/olympiad_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/olympiad_bench/olympiad_bench_adapter.py,sha256=zePVmGjmyuwCWVb4h1PIQKAIFqBehwRwO2WOD0KX_ik,6565
+evalscope/benchmarks/olympiad_bench/utils.py,sha256=w7vEZcT3vCVq8_DSMgAjZPpVFVHStJPJYsPkrs-yOFM,21412
+evalscope/benchmarks/omni_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/omni_bench/omni_bench_adapter.py,sha256=IJkRSokQC6MF_pN46Yofr_NaZaNt1XZFX1PUBmX4-qA,3651
 evalscope/benchmarks/process_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/process_bench/process_bench_adapter.py,sha256=XN3F6NH7mF4ibwGX5nI01sqEHz05UQFnBAyfAe14QYE,6174
 evalscope/benchmarks/race/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/race/race_adapter.py,sha256=KibT9gHpIOZhTcWihG0dUDAX4gAHa2g1WdGPOcEP9OY,1705
+evalscope/benchmarks/real_world_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/real_world_qa/real_world_qa_adapter.py,sha256=J2u0J9d31uvkoz9nBI9tCMqG27hmYwdLQPPef9jx_pg,2788
 evalscope/benchmarks/simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=_duveAliSaPUqVSLQ2TtSv5sfwvFFy7t-MgIIokQ24s,9017
 evalscope/benchmarks/super_gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -240,7 +267,7 @@ evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py,sha256=SPqpBebiHj_oyEqU94p
 evalscope/benchmarks/super_gpqa/utils.py,sha256=OK_oT-DnWNssITEwu_Zc3Ty5v21n0IaJQYftK2cpwmQ,3401
 evalscope/benchmarks/tau_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/tau_bench/generation.py,sha256=d7J5xrxEI-0BYxdSuxdDavcR7f1ipBdpQsKZzwyzGds,5190
-evalscope/benchmarks/tau_bench/tau_bench_adapter.py,sha256=1Dj5r9zMuLJ59wHusEcHVTszBE8BVhAK8lNZzBBzKT8,6375
+evalscope/benchmarks/tau_bench/tau_bench_adapter.py,sha256=47wA0ia6gezA3nqvUpd4Pb8f5alCrBKEt7GOxJFupow,6464
 evalscope/benchmarks/text2image/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/text2image/evalmuse_adapter.py,sha256=g-Wc1qTg-xWLTjiZPo8zmQud75ac-8mBpYRxOHfiO0g,3024
 evalscope/benchmarks/text2image/genai_bench_adapter.py,sha256=1GDB3gS9zwrfb9C83LQdQyN7bvvqeYuu5ulJ9Igmi2k,1876
@@ -268,14 +295,14 @@ evalscope/collections/__init__.py,sha256=x05hFLrjGsdtuHtc6PyQXHNuucVdYaBN9ZrM8gB
 evalscope/collections/sampler.py,sha256=086pzXQO4CO_QYCd10z149Sjh6sBpRBeIHf5OTLOVu8,4896
 evalscope/collections/schema.py,sha256=yzAlnH0O7iiWB4UnkFXI_Dvxcsq9hDgl0aGK2OpyBY8,4158
 evalscope/evaluator/__init__.py,sha256=KzYmVTfU-1pdX7va7l3B1-5QKWG07hj1B7rYkMmxitY,91
-evalscope/evaluator/evaluator.py,sha256=mkq85ieBRSc5X2FFxijomb2jD3YDKR6UelKFVP6WT8Y,13592
+evalscope/evaluator/evaluator.py,sha256=o99m1CF7xuc3Qn2M25AhWulothZxICwZgZiWxSbynTc,14435
 evalscope/filters/__init__.py,sha256=AsXwKYDjGhFsJvtj036PRjMOPsHGt-CRicnHTtM_qA4,51
 evalscope/filters/extraction.py,sha256=KLFr_3XYsrv0PTvmXy0ugj2sqv2ZOWJFV7G_MmGjTHk,4146
 evalscope/filters/selection.py,sha256=yiJu2JjXDH_lgfEtB9umkGcA3zpo3zvnyoq2mKrXbnw,1609
 evalscope/metrics/__init__.py,sha256=1giVHESSjn98uBiAvYm5uLsmRQwmf9NHPSt7OT_QJss,1615
 evalscope/metrics/llm_judge.py,sha256=XukhH9PQtIZAcbjJlOmOD9ye3ngRv_IGKKJE9jhheOE,8653
 evalscope/metrics/math_parser.py,sha256=BMfautQtNNiF9f2DIEfO6SXSn_GYhzaddAjGWG10MJA,17257
-evalscope/metrics/metric.py,sha256=6la8Nq2E_brArDcNwkbRX3ECef0AAE3IrBCfUVE7UKc,10176
+evalscope/metrics/metric.py,sha256=CabKKEbw_DptyH1ZQju7WzjB47fWUKdOhFB1ROpUC-4,10871
 evalscope/metrics/metrics.py,sha256=VxAggzEfaLKxWcXyuve8QbEBwV2W71udVyt0gynzGec,14134
 evalscope/metrics/rouge_metric.py,sha256=bqvSotuDdC0MEKmt8v6y6tBTBx0S3Ma-tfF-cMCckA4,4645
 evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
@@ -384,47 +411,47 @@ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugmen
 evalscope/models/__init__.py,sha256=RmW2S31BHBhMN49_VVF_5PJAk-TsuZQkuF2ALShbhAw,556
 evalscope/models/image_edit_model.py,sha256=oVjGgebnFu3ZXBJLNn62rJ65fcJR7DlG4qEVxisPJ2Y,4104
 evalscope/models/mockllm.py,sha256=t1fFAHkEb1n_atOCfnGteCX3DWp774lnWcHzi5lBjwM,2511
-evalscope/models/model_apis.py,sha256=qzoksjHJHE8CLoNT0UlnFVkmeS7ufguiAtaxZSC5Djc,1957
+evalscope/models/model_apis.py,sha256=ZkZ_nfbeAFJnCndRvRIRLcbmJFTMhGRBi-WfMu0uZKE,1922
 evalscope/models/modelscope.py,sha256=jSFkho_Ir2py54y_Bwj9jpCoY2mMKkZ8ORzne-ldAIE,15806
 evalscope/models/openai_compatible.py,sha256=2uK78nDhWwgph7hcIiMc3NHRbIwvswRDM9o9ENahj4k,4659
 evalscope/models/text2image_model.py,sha256=Sdiyw6vewjVTiXK8RFEh1pohOhDge80EoIWYpnLjr5Y,3929
-evalscope/models/utils/openai.py,sha256=xnnpPKWAsqqEscOQr0WJjr7gHUa9POs55Bs1Zv6MXNQ,28182
+evalscope/models/utils/openai.py,sha256=0DzuvTQYFEqcTp6sVtB2VZY7xeyWcOS0I6votqWegUg,28130
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/arguments.py,sha256=lG2IOOzxg29pdnF6IobzPcqEcYqopulFpVU2QzRaEJA,11429
+evalscope/perf/arguments.py,sha256=FmwVE4gC09B8nLd0sdczeEA9b5ztv4kwhOvLuby4wI8,11695
 evalscope/perf/benchmark.py,sha256=nSJr8lQvHDYiG33tNhkYaVOYONjhJ2wUb1x5RlUiXRY,7968
 evalscope/perf/http_client.py,sha256=4Ov1Cwi7gMgO05ZmazwyfYjUGAQNGWn7nbfl1ljRNh4,4610
 evalscope/perf/main.py,sha256=WZbBgFhIj9KqxzC7_NZxDlou019_EXatsHRt5vqDhFg,3439
 evalscope/perf/plugin/__init__.py,sha256=Ztj4h1_JYJqbbWkeuDTj5aTRyGQf5Woc4xEIyjcokVU,94
 evalscope/perf/plugin/registry.py,sha256=GhLe-h1rGzya2bgIUaV5VymQIaHqI7h5SG_i4PoGAm8,1967
 evalscope/perf/plugin/api/__init__.py,sha256=7RsGdYTSfnW6iVpveEzNu8v4x8Yc8H-Kk39DqOHMrd4,152
-evalscope/perf/plugin/api/base.py,sha256=9cX4xwTzy5ycnWqmQqRGMLasTEX6jVlobtADkh1KwXE,2782
+evalscope/perf/plugin/api/base.py,sha256=RRZVk9MFuBwb9PFPTklFhQ_RTihg_E7W_LR26-ldPIA,2782
 evalscope/perf/plugin/api/custom_api.py,sha256=VYJO2lUt9EKdWz6zeYCfvdI0MqfcsIgcKvxqvY5C-3k,10376
 evalscope/perf/plugin/api/dashscope_api.py,sha256=Miv2pzMa6sxZyYYJhCzcbOI_QHuZx7tazKpb6Not7ck,3627
-evalscope/perf/plugin/api/default_api.py,sha256=kjuHQ-zRHe5WU4ofSzWBpWbIxBQBOh_ucu1z2g62gWg,4315
-evalscope/perf/plugin/api/openai_api.py,sha256=oewwOPhv0BLdC7n3BUngpVrDYst5wMrBEPhN8oGMKNU,7703
+evalscope/perf/plugin/api/default_api.py,sha256=qvMIjbe_rM13cDHcFCwjtCsjc11qE80Yg7LypaSNTXc,4251
+evalscope/perf/plugin/api/openai_api.py,sha256=a6w4C_voza61trHskHaWNPFr2x2zhRVwIXdiNnMH81E,10570
 evalscope/perf/plugin/datasets/__init__.py,sha256=qzeQ9BrJhiJJm1wHaFeOQkvXXdSd15Ucspbn5zjs-6Q,495
 evalscope/perf/plugin/datasets/base.py,sha256=-3Ihnp2hYvZyPnP8Gh2Pu8ovlLNFHyZnNgRu3WHG4d0,2714
 evalscope/perf/plugin/datasets/custom.py,sha256=yoRHTvTGAglaZ-mmRkPjYNMG7uZYuT1_KrBxnl2i0qg,1385
-evalscope/perf/plugin/datasets/flickr8k.py,sha256=M-w1UjOMkA6Uh9v-SURDrm1YCL-m1Cn1u1cIcEJFDpY,1044
-evalscope/perf/plugin/datasets/kontext_bench.py,sha256=-KsoXS7nAd6hzN4oCe85zcLkZQT-1IGWQFThuuvE7vo,1092
+evalscope/perf/plugin/datasets/flickr8k.py,sha256=nhHiGNhXX-2c17NQ5q5Q7FgV2hB8XVeeAP8dKkboyHE,1033
+evalscope/perf/plugin/datasets/kontext_bench.py,sha256=cN70hiBX1940IWvNWZG9YGE4vO1yj41Bo7bqmOWusoQ,1081
 evalscope/perf/plugin/datasets/line_by_line.py,sha256=F4ppdjKKLzFNf_16h6S-6nAU4lOfOFI2-tPgIeZDTMA,996
 evalscope/perf/plugin/datasets/longalpaca.py,sha256=JjPGYP8NdPmP48wff2fL5IZQfajXL5qhZBvKmZxtfW4,1336
 evalscope/perf/plugin/datasets/openqa.py,sha256=5PqqiIvNTLlRrPb8PWqMGQyWRb6LuIqipYn67-xd-dY,1519
 evalscope/perf/plugin/datasets/random_dataset.py,sha256=NNAXvgFPkLDOSpYNex1DyE4X-ELtQRm13_oBooO30j8,3514
-evalscope/perf/plugin/datasets/random_vl_dataset.py,sha256=F3yA9Ih3YO895lZKCo3i85LeKTzjvGcvhzc8UNN-gUI,3240
+evalscope/perf/plugin/datasets/random_vl_dataset.py,sha256=e6exWQnupWkTDNwt2MmEK-hccuxEDmWLJRMM70onKi0,3230
 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=aoT7JD2zAzBeuZUfncKhJ2odX_7KnymwOmNB1Upam2c,935
-evalscope/perf/utils/benchmark_util.py,sha256=V91JwpiR66tOz3N5RPp3Es29M9BghdCHj_Czb0FBekI,7274
+evalscope/perf/utils/benchmark_util.py,sha256=A5d--rCElabDOl6Aaxqnu0fNR5c763YZwKIHBSeTK00,7294
 evalscope/perf/utils/db_util.py,sha256=HAISq6M7xCD2gjUEqqfbK3FjBxA-tvr_n-751tU9ypo,11634
 evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
 evalscope/perf/utils/local_server.py,sha256=_lSPlNEnOmPA_DtREgPS_vj2w_7D8PPSpypXbb0YfJM,4880
 evalscope/perf/utils/log_utils.py,sha256=NWSK_ITG4yoVx5GMLbIRGDoXSs90s7X3mftdm37Os2U,1666
 evalscope/perf/utils/rich_display.py,sha256=AQmXv1EuA1-IGgco-Jy1NLOmTKv4eBFH2K4QS8OoGVo,8206
 evalscope/report/__init__.py,sha256=DTigCg9fkU_zGNDqIaZy3CWYbrlvODvCxCTVqSx6ano,875
-evalscope/report/combinator.py,sha256=MAiOCj_q5mXm8-3lARvCSG12jUVEdJ8VcoEHJapoWzo,4134
+evalscope/report/combinator.py,sha256=Xzlhs7kwfI6cgs7rngxhvsur0bCJkrM0tAy6isq2VME,3235
 evalscope/report/generator.py,sha256=t2R3WGa4SowTRUPOgITtyTR4QDiJ6i3FH__byDKZU8Y,4959
-evalscope/report/report.py,sha256=KxboijAVNENxYHjiwyyqW_aQZ0F2CyJ6MbqUJTRHJMs,8273
+evalscope/report/report.py,sha256=lEBD_E_RJiydFTaGFNLIMTFxNrqv8QcLZb_iuUg5HB0,8479
 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
@@ -464,12 +491,12 @@ evalscope/utils/__init__.py,sha256=5OH8cOoX3YKMKUu0dMRvwzckXligIbUV-1jjJNXlpGI,2
 evalscope/utils/argument_utils.py,sha256=D7qOH85wf7LKh_cJ2X51OEaL7CMaddydmHZkfoYpvLk,1952
 evalscope/utils/chat_service.py,sha256=sSki2pKGQP3UjcIf_lbO06afI-vsaUAqglwX__wUDEw,8766
 evalscope/utils/deprecation_utils.py,sha256=aDv3HFNcJFZ7rxNgALQP0-ITO8L23HC_RX-C_m2i34Y,1610
-evalscope/utils/function_utils.py,sha256=a752Z4Xb1rznnLJU9g5Pxqd3r_XzfLzAkdcjSX0kOVc,650
-evalscope/utils/import_utils.py,sha256=b6N2x5kB_TMCkSKBlBZ5kL-x-eo_B_DWRQKtsxYL-WM,3808
-evalscope/utils/io_utils.py,sha256=q26SU80VvLi1e--KDbMmIjuw3ex_WEWzkgLkmsK9n1g,11191
-evalscope/utils/json_schema.py,sha256=MLCS8cSLXF83UPebBaVWDfXJnf0qXsXnr-bIRG88cI4,7485
-evalscope/utils/logger.py,sha256=SPhhXo9gyZtWDYDLumII2CEmwHsaW8Bu1IjK5UqWrKQ,5273
-evalscope/utils/model_utils.py,sha256=rzEnlwWgupkH1vmmv-tL9-udpwHuiQlZhbX9fXPEcZg,2434
+evalscope/utils/function_utils.py,sha256=E-AIzx_PKrZDGl1cBvlvqNvMa8yM2WUJ2wh73PNBXrQ,1887
+evalscope/utils/import_utils.py,sha256=S0WQ3gt4zpwJHjGcyC-604pWWExg3JV7f3wzoOH-tuo,5794
+evalscope/utils/io_utils.py,sha256=79F0p7dFxA84tIVSL_C4piJgeQQtVUfb2R_Xcd8v_cE,11615
+evalscope/utils/json_schema.py,sha256=ZExvQA-SI6SxWBx_hCmuQ2RRqwGKuywy4sTotvd2hH0,8288
+evalscope/utils/logger.py,sha256=roFk4Su4aJwsF0s-uYc5-tABnghwYPX3gpkA5QUGzK8,5675
+evalscope/utils/model_utils.py,sha256=mdtYoHhUdfpxUtnS52XZjNdO3uSK4yeIBHT3aDU7s-A,2455
 evalscope/utils/multi_choices.py,sha256=OxBER7amWpoRY0Z-o39rDmCNK6wpr1HQm9mMHpWLgp0,9524
 evalscope/utils/url_utils.py,sha256=9HcFt9uZNbOJR3ADUFQ_dBFKziHV6H66Df7HYs1M4Po,1757
 tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -477,17 +504,18 @@ tests/common.py,sha256=BB136KcGaEfdWqMwApa48K0CTSGmOCUZ0FYDqpfYnAA,2423
 tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
 tests/utils.py,sha256=Fgm0CU6ilZjCGOfOMJH-Trxy0UIAGbhvy0Ijy_zDGUk,323
 tests/benchmark/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/benchmark/test_eval.py,sha256=Grms3aMWQONexSsSvOSxkoURHLJ2Z0SqBjrcVWDoMRs,12455
+tests/benchmark/test_eval.py,sha256=vSAvhiCKxHpjHdGhZn8l0qzPSiG1ZZafz_M06B_a8_Y,13827
 tests/benchmark/test_image_edit.py,sha256=z3z7psMRFynpVgUAFoH--ieeGXzb9cHkrq3tT_sCZo8,2165
+tests/benchmark/test_sandbox.py,sha256=bHyX8ammdn7EsEbN80cIzDNhQZlJD3Ssoj9l4efF7rI,2968
 tests/benchmark/test_t2i.py,sha256=fciaGsOrkOpT4WQlsnmjrqw6qolCzI0DGyWQAJkM-Es,4513
-tests/benchmark/test_vlm.py,sha256=k2DC0zWO2TtVSf-MP-n-wGwfk9MWKKd6hZzkC4nlUO0,2541
+tests/benchmark/test_vlm.py,sha256=gn0ledf_yPY1IhCyCtiqT_dTVPUVZ3NVPr9yzsC_UZQ,4501
 tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/cli/test_all.py,sha256=1omOXC1lBphBLm0hTf5HNstlF_bwi16dYyr00gvaCTM,7301
 tests/cli/test_collection.py,sha256=lGz3YUS_0gM6_HjQLe26OfBAkHOPOEDWMO-UyP58GN8,4455
 tests/cli/test_custom.py,sha256=9z_N7Re712xI62TqVSTBdzB_iFFEUb55wcWIcGvJb84,9254
 tests/cli/test_reasoning.py,sha256=rU181LLoKbFCpNPFCIZULxEgsJ2PYswel2pP2EsjEmo,2696
 tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=yqm3abB5ZdNPKaJkvzMvfcz-Cz_o2RxUZ3ZnqgRb-tQ,5937
+tests/perf/test_perf.py,sha256=ugYNEyU32ctryPFa_6fr8aQYxfHJMymdKnKKEHM9Ajc,6174
 tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/rag/test_clip_benchmark.py,sha256=qpSLgmHMGcYTnxP7AI__y-ii5_tu_fCSht6p3TBetkA,2650
 tests/rag/test_mteb.py,sha256=fdNQIyUEzE7puPCKw5QhCHTEu7hz-ieHeq1xCWGh6IM,7246
@@ -498,9 +526,9 @@ tests/swift/test_run_swift_vlm_eval.py,sha256=RwrKkc1WHEZxetM11cGL81G4faKCn7SYn4
 tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=UAUtOCQ72xbm8s-sov3cBEpYVDy189wpB-qOL3KoU7M,6053
 tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/vlm/test_vlmeval.py,sha256=EDQRkYfSyOICUwo_tm3p-puaE_xdFmqOPkrt5etxsqM,3307
-evalscope-1.0.1.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-1.0.1.dist-info/METADATA,sha256=2XzuX9tVYzONuLHVq2WsQ_uaWImGVwiY2IPAJhpNEOA,40287
-evalscope-1.0.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-1.0.1.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-1.0.1.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-1.0.1.dist-info/RECORD,,
+evalscope-1.0.2.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-1.0.2.dist-info/METADATA,sha256=vZciS7qNosSJOdwyRSxsCyVqvw8hyqKS84yKjlbxwzw,40305
+evalscope-1.0.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-1.0.2.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-1.0.2.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-1.0.2.dist-info/RECORD,,

tests/benchmark/test_eval.py

@@ -33,12 +33,13 @@ class TestNativeBenchmark(TestBenchmark):
             'judge_strategy': JudgeStrategy.AUTO,
             'judge_worker_num': 5,
             'judge_model_args': {
-                'model_id': 'qwen2.5-72b-instruct',
+                'model_id': 'qwen3-235b-a22b',
                 'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
                 'api_key': env.get('DASHSCOPE_API_KEY'),
                 'generation_config': {
                     'temperature': 0.0,
                     'max_tokens': 4096,
+                    'extra_body': {'enable_thinking': False}
                 }
             },
             'debug': True,
@@ -65,6 +66,14 @@ class TestNativeBenchmark(TestBenchmark):
         }
         self._run_dataset_test('mmlu', use_mock=True, dataset_args=dataset_args)
 
+    def test_mmlu_reasoning(self):
+        """Test MMLU reasoning dataset."""
+        dataset_args = {
+            'few_shot_num': 0,
+            'subset_list': ['abstract_algebra', 'computer_security']
+        }
+        self._run_dataset_test('mmlu', dataset_args=dataset_args, model='qwen3-0.6b', stream=True)
+
     def test_mmlu_pro(self):
         """Test MMLU-Pro reasoning dataset."""
         dataset_args = {
@@ -203,6 +212,7 @@ class TestNativeBenchmark(TestBenchmark):
     def test_bbh(self):
         dataset_args = {
             'subset_list': ['temporal_sequences', 'navigate'],
+            'few_shot_num': 0,
         }
         self._run_dataset_test('bbh', dataset_args=dataset_args)
 
@@ -317,20 +327,21 @@ class TestNativeBenchmark(TestBenchmark):
     def test_humaneval(self):
         """Test HumanEval dataset."""
         dataset_args = {
-            'metric_list': ['Pass@1', 'Pass@2', 'Pass@5']
+            'metric_list': ['Pass@1']
         }
-        self._run_dataset_test('humaneval', dataset_args, repeats=5)
+        self._run_dataset_test('humaneval', dataset_args)
 
     def test_live_code_bench(self):
         """Test LiveCodeBench dataset."""
         dataset_args = {
-            'subset_list': ['v6'],
+            'subset_list': ['v5'],
+            'review_timeout': 6,
             'extra_params': {
                 'start_date': '2024-08-01',
                 'end_date': '2025-02-28'
             },
         }
-        self._run_dataset_test('live_code_bench', dataset_args, judge_worker_num=1)
+        self._run_dataset_test('live_code_bench', dataset_args, limit=20, use_cache='outputs/20250918_200232', rerun_review=True)
 
     def test_tool_bench(self):
         """Test ToolBench dataset."""
@@ -339,13 +350,18 @@ class TestNativeBenchmark(TestBenchmark):
     def test_bfcl(self):
         """Test BFCL dataset."""
         dataset_args = {
-            'subset_list': ['simple', 'live_multiple', 'multi_turn_base'],
+            'subset_list': [
+                # 'simple',
+                # 'live_multiple',
+                # 'multi_turn_base',
+                'multi_turn_miss_func'
+            ],
             'extra_params': {
                 'is_fc_model': True,
                 'underscore_to_dot': True
             }
         }
-        self._run_dataset_test('bfcl_v3', dataset_args, model='qwq-plus', stream=True)
+        self._run_dataset_test('bfcl_v3', dataset_args, model='qwen-plus', limit=30, eval_batch_size=5)
 
     def test_tau_bench(self):
         dataset_args = {
@@ -378,6 +394,34 @@ class TestNativeBenchmark(TestBenchmark):
         }
         self._run_dataset_test('data_collection', dataset_args)
 
+    def test_multi_if(self):
+        dataset_args = {
+            'subset_list': ['English', 'Chinese'],
+            'few_shot_num': 0,
+        }
+        self._run_dataset_test('multi_if', dataset_args, limit=5)
+
+    def test_healthbench(self):
+        dataset_args = {
+            'subset_list': ['health_data_tasks'],
+            'extra_params': {
+                'version': 'Hard'
+            }
+        }
+        self._run_dataset_test('health_bench', dataset_args, limit=5)
+
+
+    def test_amc(self):
+        dataset_args = {
+            'subset_list': ['amc22'],
+        }
+        self._run_dataset_test('amc', dataset_args)
+
+    def test_minerva_math(self):
+        dataset_args = {
+            'subset_list': ['default'],
+        }
+        self._run_dataset_test('minerva_math', dataset_args)
 
 if __name__ == '__main__':
     # Run specific test: python -m unittest test_eval.TestBenchmark.test_gsm8k

tests/benchmark/test_sandbox.py

@@ -0,0 +1,81 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+from dotenv import dotenv_values
+
+env = dotenv_values('.env')
+
+import unittest
+
+from evalscope.constants import EvalType, JudgeStrategy, OutputType
+from evalscope.utils.logger import get_logger
+from tests.common import TestBenchmark
+
+logger = get_logger()
+
+
+class TestCodeBenchmark(TestBenchmark):
+    """Benchmark evaluation test cases."""
+
+    def setUp(self):
+        """Setup common test configuration."""
+        self.base_config = {
+            'model': 'qwen-plus',
+            'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+            'api_key': env.get('DASHSCOPE_API_KEY'),
+            'eval_type': EvalType.SERVICE,
+            'eval_batch_size': 5,
+            'limit': 5,
+            'generation_config': {
+                'max_tokens': 4096,
+                'temperature': 0.0,
+                'seed': 42,
+                'parallel_tool_calls': True
+            },
+            'judge_strategy': JudgeStrategy.AUTO,
+            'judge_worker_num': 5,
+            'judge_model_args': {
+                'model_id': 'qwen2.5-72b-instruct',
+                'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+                'api_key': env.get('DASHSCOPE_API_KEY'),
+                'generation_config': {
+                    'temperature': 0.0,
+                    'max_tokens': 4096,
+                }
+            },
+            'use_sandbox': True,
+            'sandbox_type': 'docker',
+            'debug': True,
+        }
+
+    def test_humaneval(self):
+        """Test Humaneval dataset."""
+        self._run_dataset_test('humaneval', limit=5)
+
+    def test_humaneval_remote_sandbox(self):
+        """Test Humaneval dataset with remote sandbox manager."""
+        sandbox_manager_config = {'base_url': 'http://localhost:8000'}
+        self._run_dataset_test('humaneval', limit=5, sandbox_manager_config=sandbox_manager_config)
+
+    def test_live_code_bench(self):
+        """Test Live Code Bench dataset."""
+        dataset_args = {
+            'subset_list': ['v5'],
+            'review_timeout': 6,
+            'extra_params': {
+                'start_date': '2024-08-01',
+                'end_date': '2025-02-28'
+            },
+        }
+        self._run_dataset_test('live_code_bench', limit=5, dataset_args=dataset_args, use_cache='outputs/20250918_200232', rerun_review=True)
+
+    def test_live_code_bench_remote_sandbox(self):
+        """Test Live Code Bench dataset."""
+        dataset_args = {
+            'subset_list': ['v5'],
+            'review_timeout': 6,
+            'extra_params': {
+                'start_date': '2024-08-01',
+                'end_date': '2025-02-28'
+            },
+        }
+        sandbox_manager_config = {'base_url': 'http://localhost:8000'}
+        self._run_dataset_test('live_code_bench', limit=20, dataset_args=dataset_args, sandbox_manager_config=sandbox_manager_config, use_cache='outputs/20250918_200232_2', rerun_review=True)

tests/benchmark/test_vlm.py

@@ -25,7 +25,7 @@ class TestVLMBenchmark(TestBenchmark):
             'eval_batch_size': 5,
             'limit': 5,
             'generation_config': {
-                'max_tokens': 4096,
+                'max_tokens': 2048,
                 'temperature': 0.0,
                 'seed': 42,
                 'parallel_tool_calls': True
@@ -72,9 +72,66 @@ class TestVLMBenchmark(TestBenchmark):
         }
         self._run_dataset_test('mmmu_pro', dataset_args=dataset_args, limit=10)
 
-    def test_qwen3_collection(self):
+    def test_qwen3_vl_collection(self):
         dataset_args = {
             'dataset_id': 'outputs/qwen3_vl_test.jsonl',
             'shuffle': True,
         }
-        self._run_dataset_test('data_collection', dataset_args)
+        self._run_dataset_test('data_collection', dataset_args, limit=100)
+
+    def test_real_world_qa(self):
+        dataset_args = {
+            'subset_list': ['default']
+        }
+        self._run_dataset_test('real_world_qa', dataset_args=dataset_args, limit=10)
+
+    def test_ai2d(self):
+        dataset_args = {
+            'subset_list': ['default']
+        }
+        self._run_dataset_test('ai2d', dataset_args=dataset_args)
+
+    def test_cc_bench(self):
+        dataset_args = {
+            'subset_list': ['cc']
+        }
+        self._run_dataset_test('cc_bench', dataset_args=dataset_args)
+
+    def test_mm_bench(self):
+        dataset_args = {
+            'subset_list': ['cn', 'en']
+        }
+        self._run_dataset_test('mm_bench', dataset_args=dataset_args)
+
+    def test_mm_star(self):
+        dataset_args = {
+            # 'subset_list': ['val']
+        }
+        self._run_dataset_test('mm_star', dataset_args=dataset_args)
+
+    def test_omni_bench(self):
+        dataset_args = {
+            'extra_params': {
+                'use_image': True, # Whether to use image input, if False, use text alternative image content.
+                'use_audio': True, # Whether to use audio input, if False, use text alternative audio content.
+            }
+        }
+        self._run_dataset_test('omni_bench', dataset_args=dataset_args, model='qwen-omni-turbo')
+
+    def test_olympiad_bench(self):
+        dataset_args = {
+            'subset_list': [
+                # 'OE_MM_maths_en_COMP',
+                # 'OE_MM_maths_zh_CEE',
+                # 'OE_MM_maths_zh_COMP',
+                # 'OE_MM_physics_en_COMP',
+                # 'OE_MM_physics_zh_CEE',
+                # 'OE_TO_maths_en_COMP',
+                # 'OE_TO_maths_zh_CEE',
+                # 'OE_TO_maths_zh_COMP',
+                # 'OE_TO_physics_en_COMP',
+                # 'OE_TO_physics_zh_CEE',
+                'TP_TO_maths_zh_CEE',
+            ]
+        }
+        self._run_dataset_test('olympiad_bench', dataset_args=dataset_args)