evalscope 1.0.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (324) hide show
  1. evalscope/api/benchmark/__init__.py +9 -1
  2. evalscope/api/benchmark/adapters/__init__.py +4 -0
  3. evalscope/api/benchmark/adapters/agent_adapter.py +8 -0
  4. evalscope/api/benchmark/adapters/default_data_adapter.py +75 -4
  5. evalscope/api/benchmark/adapters/image_edit_adapter.py +82 -0
  6. evalscope/api/benchmark/adapters/multi_choice_adapter.py +5 -2
  7. evalscope/api/benchmark/adapters/ner_adapter.py +212 -0
  8. evalscope/api/benchmark/adapters/text2image_adapter.py +12 -10
  9. evalscope/api/benchmark/adapters/vision_language_adapter.py +8 -0
  10. evalscope/api/benchmark/benchmark.py +85 -2
  11. evalscope/api/benchmark/meta.py +10 -1
  12. evalscope/api/dataset/dataset.py +27 -6
  13. evalscope/api/dataset/loader.py +8 -3
  14. evalscope/api/evaluator/cache.py +31 -4
  15. evalscope/api/evaluator/evaluator.py +5 -0
  16. evalscope/api/evaluator/state.py +17 -1
  17. evalscope/api/messages/__init__.py +1 -0
  18. evalscope/api/messages/chat_message.py +52 -2
  19. evalscope/api/metric/__init__.py +1 -1
  20. evalscope/api/metric/metric.py +6 -1
  21. evalscope/api/metric/scorer.py +15 -7
  22. evalscope/api/mixin/__init__.py +1 -1
  23. evalscope/api/mixin/llm_judge_mixin.py +2 -0
  24. evalscope/api/mixin/sandbox_mixin.py +182 -0
  25. evalscope/api/model/generate_config.py +10 -6
  26. evalscope/api/model/model.py +5 -2
  27. evalscope/api/tool/tool_info.py +1 -1
  28. evalscope/app/app.py +3 -0
  29. evalscope/app/ui/multi_model.py +6 -1
  30. evalscope/app/ui/single_model.py +11 -5
  31. evalscope/app/utils/data_utils.py +8 -7
  32. evalscope/app/utils/env_utils.py +12 -0
  33. evalscope/app/utils/text_utils.py +14 -12
  34. evalscope/app/utils/visualization.py +2 -2
  35. evalscope/arguments.py +8 -4
  36. evalscope/backend/opencompass/backend_manager.py +0 -2
  37. evalscope/backend/rag_eval/utils/embedding.py +9 -1
  38. evalscope/benchmarks/aa_lcr/aa_lcr_adapter.py +205 -0
  39. evalscope/benchmarks/ai2d/ai2d_adapter.py +54 -0
  40. evalscope/benchmarks/aime/aime24_adapter.py +5 -0
  41. evalscope/benchmarks/aime/aime25_adapter.py +136 -1
  42. evalscope/benchmarks/aime/grader.py +307 -0
  43. evalscope/benchmarks/aime/math_normalize.py +189 -0
  44. evalscope/benchmarks/amc/amc_adapter.py +51 -0
  45. evalscope/benchmarks/arena_hard/arena_hard_adapter.py +1 -0
  46. evalscope/benchmarks/bbh/bbh_adapter.py +43 -17
  47. evalscope/benchmarks/bfcl/{bfcl_adapter.py → v3/bfcl_v3_adapter.py} +131 -19
  48. evalscope/benchmarks/bfcl/{generation.py → v3/generation.py} +9 -9
  49. evalscope/benchmarks/bfcl/v3/utils.py +23 -0
  50. evalscope/benchmarks/bfcl/v4/__init__.py +0 -0
  51. evalscope/benchmarks/bfcl/v4/bfcl_v4_adapter.py +229 -0
  52. evalscope/benchmarks/bfcl/v4/utils.py +410 -0
  53. evalscope/benchmarks/biomix_qa/__init__.py +0 -0
  54. evalscope/benchmarks/biomix_qa/biomix_qa_adapter.py +36 -0
  55. evalscope/benchmarks/blink/__init__.py +0 -0
  56. evalscope/benchmarks/blink/blink_adapter.py +61 -0
  57. evalscope/benchmarks/ceval/ceval_adapter.py +1 -2
  58. evalscope/benchmarks/chartqa/__init__.py +0 -0
  59. evalscope/benchmarks/chartqa/chartqa_adapter.py +80 -0
  60. evalscope/benchmarks/chartqa/utils.py +38 -0
  61. evalscope/benchmarks/coin_flip/__init__.py +0 -0
  62. evalscope/benchmarks/coin_flip/coin_flip_adapter.py +128 -0
  63. evalscope/benchmarks/commonsense_qa/__init__.py +0 -0
  64. evalscope/benchmarks/commonsense_qa/commonsense_qa_adapter.py +32 -0
  65. evalscope/benchmarks/competition_math/competition_math_adapter.py +5 -0
  66. evalscope/benchmarks/data_collection/data_collection_adapter.py +24 -19
  67. evalscope/benchmarks/docvqa/__init__.py +0 -0
  68. evalscope/benchmarks/docvqa/docvqa_adapter.py +67 -0
  69. evalscope/benchmarks/drivelology/__init__.py +0 -0
  70. evalscope/benchmarks/drivelology/drivelology_binary_adapter.py +170 -0
  71. evalscope/benchmarks/drivelology/drivelology_multilabel_adapter.py +254 -0
  72. evalscope/benchmarks/drivelology/drivelology_selection_adapter.py +49 -0
  73. evalscope/benchmarks/drivelology/drivelology_writing_adapter.py +218 -0
  74. evalscope/benchmarks/drop/drop_adapter.py +15 -44
  75. evalscope/benchmarks/drop/utils.py +97 -0
  76. evalscope/benchmarks/frames/frames_adapter.py +2 -1
  77. evalscope/benchmarks/general_arena/general_arena_adapter.py +7 -2
  78. evalscope/benchmarks/general_arena/utils.py +2 -1
  79. evalscope/benchmarks/general_mcq/general_mcq_adapter.py +1 -1
  80. evalscope/benchmarks/general_qa/general_qa_adapter.py +1 -1
  81. evalscope/benchmarks/gsm8k/gsm8k_adapter.py +25 -9
  82. evalscope/benchmarks/hallusion_bench/__init__.py +0 -0
  83. evalscope/benchmarks/hallusion_bench/hallusion_bench_adapter.py +159 -0
  84. evalscope/benchmarks/halu_eval/__init__.py +0 -0
  85. evalscope/benchmarks/halu_eval/halu_eval_adapter.py +128 -0
  86. evalscope/benchmarks/halu_eval/halu_eval_instructions.py +84 -0
  87. evalscope/benchmarks/healthbench/__init__.py +0 -0
  88. evalscope/benchmarks/healthbench/healthbench_adapter.py +282 -0
  89. evalscope/benchmarks/healthbench/utils.py +102 -0
  90. evalscope/benchmarks/hle/hle_adapter.py +3 -2
  91. evalscope/benchmarks/humaneval/humaneval_adapter.py +24 -52
  92. evalscope/benchmarks/humaneval/utils.py +235 -0
  93. evalscope/benchmarks/ifeval/instructions_util.py +2 -3
  94. evalscope/benchmarks/image_edit/__init__.py +0 -0
  95. evalscope/benchmarks/image_edit/gedit/__init__.py +0 -0
  96. evalscope/benchmarks/image_edit/gedit/gedit_adapter.py +138 -0
  97. evalscope/benchmarks/image_edit/gedit/utils.py +372 -0
  98. evalscope/benchmarks/image_edit/gedit/vie_prompts.py +406 -0
  99. evalscope/benchmarks/infovqa/__init__.py +0 -0
  100. evalscope/benchmarks/infovqa/infovqa_adapter.py +66 -0
  101. evalscope/benchmarks/live_code_bench/evaluate_utils.py +13 -6
  102. evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py +66 -54
  103. evalscope/benchmarks/live_code_bench/sandbox_evaluate_utils.py +220 -0
  104. evalscope/benchmarks/logi_qa/__int__.py +0 -0
  105. evalscope/benchmarks/logi_qa/logi_qa_adapter.py +41 -0
  106. evalscope/benchmarks/math_500/math_500_adapter.py +5 -1
  107. evalscope/benchmarks/math_qa/__init__.py +0 -0
  108. evalscope/benchmarks/math_qa/math_qa_adapter.py +35 -0
  109. evalscope/benchmarks/math_verse/__init__.py +0 -0
  110. evalscope/benchmarks/math_verse/math_verse_adapter.py +105 -0
  111. evalscope/benchmarks/math_vision/__init__.py +0 -0
  112. evalscope/benchmarks/math_vision/math_vision_adapter.py +116 -0
  113. evalscope/benchmarks/math_vista/__init__.py +0 -0
  114. evalscope/benchmarks/math_vista/math_vista_adapter.py +114 -0
  115. evalscope/benchmarks/med_mcqa/__init__.py +0 -0
  116. evalscope/benchmarks/med_mcqa/med_mcqa_adapter.py +32 -0
  117. evalscope/benchmarks/minerva_math/__init__.py +0 -0
  118. evalscope/benchmarks/minerva_math/minerva_math_adapter.py +53 -0
  119. evalscope/benchmarks/mm_bench/__init__.py +0 -0
  120. evalscope/benchmarks/mm_bench/mm_bench_adapter.py +99 -0
  121. evalscope/benchmarks/mm_star/__init__.py +0 -0
  122. evalscope/benchmarks/mm_star/mm_star_adapter.py +73 -0
  123. evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py +1 -1
  124. evalscope/benchmarks/mmmu/__init__.py +0 -0
  125. evalscope/benchmarks/mmmu/mmmu_adapter.py +159 -0
  126. evalscope/benchmarks/mmmu_pro/__init__.py +0 -0
  127. evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py +124 -0
  128. evalscope/benchmarks/mri_mcqa/__init__.py +0 -0
  129. evalscope/benchmarks/mri_mcqa/mri_mcqa_adapter.py +34 -0
  130. evalscope/benchmarks/multi_if/__init__.py +0 -0
  131. evalscope/benchmarks/multi_if/ifeval.py +3354 -0
  132. evalscope/benchmarks/multi_if/metrics.py +120 -0
  133. evalscope/benchmarks/multi_if/multi_if_adapter.py +161 -0
  134. evalscope/benchmarks/music_trivia/__init__.py +0 -0
  135. evalscope/benchmarks/music_trivia/music_trivia_adapter.py +36 -0
  136. evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py +7 -6
  137. evalscope/benchmarks/ner/__init__.py +0 -0
  138. evalscope/benchmarks/ner/broad_twitter_corpus_adapter.py +52 -0
  139. evalscope/benchmarks/ner/conll2003_adapter.py +48 -0
  140. evalscope/benchmarks/ner/copious_adapter.py +85 -0
  141. evalscope/benchmarks/ner/cross_ner_adapter.py +120 -0
  142. evalscope/benchmarks/ner/cross_ner_entities/__init__.py +0 -0
  143. evalscope/benchmarks/ner/cross_ner_entities/ai.py +54 -0
  144. evalscope/benchmarks/ner/cross_ner_entities/literature.py +36 -0
  145. evalscope/benchmarks/ner/cross_ner_entities/music.py +39 -0
  146. evalscope/benchmarks/ner/cross_ner_entities/politics.py +37 -0
  147. evalscope/benchmarks/ner/cross_ner_entities/science.py +58 -0
  148. evalscope/benchmarks/ner/genia_ner_adapter.py +66 -0
  149. evalscope/benchmarks/ner/harvey_ner_adapter.py +58 -0
  150. evalscope/benchmarks/ner/mit_movie_trivia_adapter.py +74 -0
  151. evalscope/benchmarks/ner/mit_restaurant_adapter.py +66 -0
  152. evalscope/benchmarks/ner/ontonotes5_adapter.py +87 -0
  153. evalscope/benchmarks/ner/wnut2017_adapter.py +61 -0
  154. evalscope/benchmarks/ocr_bench/__init__.py +0 -0
  155. evalscope/benchmarks/ocr_bench/ocr_bench/__init__.py +0 -0
  156. evalscope/benchmarks/ocr_bench/ocr_bench/ocr_bench_adapter.py +101 -0
  157. evalscope/benchmarks/ocr_bench/ocr_bench_v2/IoUscore_metric.py +87 -0
  158. evalscope/benchmarks/ocr_bench/ocr_bench_v2/TEDS_metric.py +963 -0
  159. evalscope/benchmarks/ocr_bench/ocr_bench_v2/__init__.py +0 -0
  160. evalscope/benchmarks/ocr_bench/ocr_bench_v2/ocr_bench_v2_adapter.py +161 -0
  161. evalscope/benchmarks/ocr_bench/ocr_bench_v2/page_ocr_metric.py +50 -0
  162. evalscope/benchmarks/ocr_bench/ocr_bench_v2/parallel.py +46 -0
  163. evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/__init__.py +0 -0
  164. evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/readme.txt +26 -0
  165. evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/rrc_evaluation_funcs_1_1.py +537 -0
  166. evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/script.py +481 -0
  167. evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_metric.py +179 -0
  168. evalscope/benchmarks/ocr_bench/ocr_bench_v2/utils.py +433 -0
  169. evalscope/benchmarks/ocr_bench/ocr_bench_v2/vqa_metric.py +254 -0
  170. evalscope/benchmarks/olympiad_bench/__init__.py +0 -0
  171. evalscope/benchmarks/olympiad_bench/olympiad_bench_adapter.py +163 -0
  172. evalscope/benchmarks/olympiad_bench/utils.py +565 -0
  173. evalscope/benchmarks/omni_bench/__init__.py +0 -0
  174. evalscope/benchmarks/omni_bench/omni_bench_adapter.py +86 -0
  175. evalscope/benchmarks/omnidoc_bench/__init__.py +0 -0
  176. evalscope/benchmarks/omnidoc_bench/end2end_eval.py +349 -0
  177. evalscope/benchmarks/omnidoc_bench/metrics.py +547 -0
  178. evalscope/benchmarks/omnidoc_bench/omnidoc_bench_adapter.py +135 -0
  179. evalscope/benchmarks/omnidoc_bench/utils.py +1937 -0
  180. evalscope/benchmarks/piqa/__init__.py +0 -0
  181. evalscope/benchmarks/piqa/piqa_adapter.py +32 -0
  182. evalscope/benchmarks/poly_math/__init__.py +0 -0
  183. evalscope/benchmarks/poly_math/poly_math_adapter.py +132 -0
  184. evalscope/benchmarks/poly_math/utils/instruction.py +105 -0
  185. evalscope/benchmarks/pope/__init__.py +0 -0
  186. evalscope/benchmarks/pope/pope_adapter.py +112 -0
  187. evalscope/benchmarks/process_bench/process_bench_adapter.py +1 -0
  188. evalscope/benchmarks/pumed_qa/__init__.py +0 -0
  189. evalscope/benchmarks/pumed_qa/pubmed_qa_adapter.py +175 -0
  190. evalscope/benchmarks/qasc/__init__.py +0 -0
  191. evalscope/benchmarks/qasc/qasc_adapter.py +35 -0
  192. evalscope/benchmarks/real_world_qa/__init__.py +0 -0
  193. evalscope/benchmarks/real_world_qa/real_world_qa_adapter.py +64 -0
  194. evalscope/benchmarks/sciq/__init__.py +0 -0
  195. evalscope/benchmarks/sciq/sciq_adapter.py +36 -0
  196. evalscope/benchmarks/seed_bench_2_plus/__init__.py +0 -0
  197. evalscope/benchmarks/seed_bench_2_plus/seed_bench_2_plus_adapter.py +72 -0
  198. evalscope/benchmarks/simple_qa/simple_qa_adapter.py +1 -1
  199. evalscope/benchmarks/simple_vqa/__init__.py +0 -0
  200. evalscope/benchmarks/simple_vqa/simple_vqa_adapter.py +169 -0
  201. evalscope/benchmarks/siqa/__init__.py +0 -0
  202. evalscope/benchmarks/siqa/siqa_adapter.py +39 -0
  203. evalscope/benchmarks/tau_bench/tau2_bench/__init__.py +0 -0
  204. evalscope/benchmarks/tau_bench/tau2_bench/generation.py +158 -0
  205. evalscope/benchmarks/tau_bench/tau2_bench/tau2_bench_adapter.py +146 -0
  206. evalscope/benchmarks/tau_bench/tau_bench/__init__.py +0 -0
  207. evalscope/benchmarks/tau_bench/{generation.py → tau_bench/generation.py} +1 -1
  208. evalscope/benchmarks/tau_bench/{tau_bench_adapter.py → tau_bench/tau_bench_adapter.py} +29 -29
  209. evalscope/benchmarks/text2image/__init__.py +0 -0
  210. evalscope/benchmarks/{aigc/t2i → text2image}/evalmuse_adapter.py +3 -1
  211. evalscope/benchmarks/{aigc/t2i → text2image}/genai_bench_adapter.py +2 -2
  212. evalscope/benchmarks/{aigc/t2i → text2image}/general_t2i_adapter.py +1 -1
  213. evalscope/benchmarks/{aigc/t2i → text2image}/hpdv2_adapter.py +7 -2
  214. evalscope/benchmarks/{aigc/t2i → text2image}/tifa_adapter.py +1 -0
  215. evalscope/benchmarks/tool_bench/tool_bench_adapter.py +3 -3
  216. evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +1 -2
  217. evalscope/benchmarks/visu_logic/__init__.py +0 -0
  218. evalscope/benchmarks/visu_logic/visu_logic_adapter.py +75 -0
  219. evalscope/benchmarks/wmt/__init__.py +0 -0
  220. evalscope/benchmarks/wmt/wmt24_adapter.py +294 -0
  221. evalscope/benchmarks/zerobench/__init__.py +0 -0
  222. evalscope/benchmarks/zerobench/zerobench_adapter.py +64 -0
  223. evalscope/cli/start_app.py +7 -1
  224. evalscope/cli/start_perf.py +7 -1
  225. evalscope/config.py +103 -18
  226. evalscope/constants.py +18 -0
  227. evalscope/evaluator/evaluator.py +138 -82
  228. evalscope/metrics/bert_score/__init__.py +0 -0
  229. evalscope/metrics/bert_score/scorer.py +338 -0
  230. evalscope/metrics/bert_score/utils.py +697 -0
  231. evalscope/metrics/llm_judge.py +19 -7
  232. evalscope/metrics/math_parser.py +14 -0
  233. evalscope/metrics/metric.py +317 -13
  234. evalscope/metrics/metrics.py +37 -0
  235. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/config.py +0 -0
  236. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/dist_utils.py +0 -0
  237. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/gradcam.py +0 -0
  238. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/logger.py +0 -0
  239. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/optims.py +0 -0
  240. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/registry.py +0 -0
  241. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/utils.py +0 -0
  242. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/__init__.py +0 -0
  243. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py +0 -0
  244. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py +0 -0
  245. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py +2 -6
  246. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py +2 -6
  247. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py +2 -6
  248. evalscope/models/image_edit_model.py +125 -0
  249. evalscope/models/model_apis.py +22 -0
  250. evalscope/models/openai_compatible.py +21 -0
  251. evalscope/models/text2image_model.py +2 -2
  252. evalscope/models/utils/openai.py +16 -6
  253. evalscope/perf/arguments.py +26 -4
  254. evalscope/perf/benchmark.py +76 -89
  255. evalscope/perf/http_client.py +31 -16
  256. evalscope/perf/main.py +15 -2
  257. evalscope/perf/plugin/api/base.py +9 -7
  258. evalscope/perf/plugin/api/custom_api.py +13 -58
  259. evalscope/perf/plugin/api/default_api.py +188 -79
  260. evalscope/perf/plugin/api/openai_api.py +85 -20
  261. evalscope/perf/plugin/datasets/base.py +21 -0
  262. evalscope/perf/plugin/datasets/custom.py +2 -3
  263. evalscope/perf/plugin/datasets/flickr8k.py +2 -2
  264. evalscope/perf/plugin/datasets/kontext_bench.py +2 -2
  265. evalscope/perf/plugin/datasets/line_by_line.py +2 -3
  266. evalscope/perf/plugin/datasets/longalpaca.py +2 -3
  267. evalscope/perf/plugin/datasets/openqa.py +2 -4
  268. evalscope/perf/plugin/datasets/random_dataset.py +1 -3
  269. evalscope/perf/plugin/datasets/random_vl_dataset.py +2 -2
  270. evalscope/perf/utils/benchmark_util.py +43 -27
  271. evalscope/perf/utils/db_util.py +14 -19
  272. evalscope/perf/utils/local_server.py +3 -44
  273. evalscope/perf/utils/log_utils.py +21 -6
  274. evalscope/report/__init__.py +13 -3
  275. evalscope/report/combinator.py +91 -20
  276. evalscope/report/generator.py +8 -87
  277. evalscope/report/report.py +8 -4
  278. evalscope/run.py +13 -5
  279. evalscope/third_party/toolbench_static/llm/swift_infer.py +0 -4
  280. evalscope/utils/argument_utils.py +1 -1
  281. evalscope/utils/chat_service.py +1 -1
  282. evalscope/utils/function_utils.py +249 -12
  283. evalscope/utils/import_utils.py +73 -1
  284. evalscope/utils/io_utils.py +132 -7
  285. evalscope/utils/json_schema.py +25 -2
  286. evalscope/utils/logger.py +69 -18
  287. evalscope/utils/model_utils.py +4 -3
  288. evalscope/utils/multi_choices.py +39 -7
  289. evalscope/utils/ner.py +377 -0
  290. evalscope/version.py +2 -2
  291. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info}/METADATA +252 -408
  292. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info}/RECORD +290 -154
  293. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info}/WHEEL +1 -1
  294. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info}/top_level.txt +0 -1
  295. evalscope/api/mixin/dataset_mixin.py +0 -105
  296. evalscope/benchmarks/aigc/i2i/general_i2i_adapter.py +0 -44
  297. tests/__init__.py +0 -1
  298. tests/aigc/__init__.py +0 -1
  299. tests/aigc/test_t2i.py +0 -142
  300. tests/benchmark/__init__.py +0 -1
  301. tests/benchmark/test_eval.py +0 -386
  302. tests/cli/__init__.py +0 -1
  303. tests/cli/test_all.py +0 -229
  304. tests/cli/test_collection.py +0 -96
  305. tests/cli/test_custom.py +0 -268
  306. tests/perf/__init__.py +0 -1
  307. tests/perf/test_perf.py +0 -176
  308. tests/rag/test_clip_benchmark.py +0 -90
  309. tests/rag/test_mteb.py +0 -213
  310. tests/rag/test_ragas.py +0 -128
  311. tests/swift/__init__.py +0 -1
  312. tests/swift/test_run_swift_eval.py +0 -146
  313. tests/swift/test_run_swift_vlm_eval.py +0 -128
  314. tests/swift/test_run_swift_vlm_jugde_eval.py +0 -157
  315. tests/test_run_all.py +0 -12
  316. tests/utils.py +0 -13
  317. tests/vlm/__init__.py +0 -1
  318. tests/vlm/test_vlmeval.py +0 -102
  319. /evalscope/benchmarks/{aigc → aa_lcr}/__init__.py +0 -0
  320. /evalscope/benchmarks/{aigc/i2i → ai2d}/__init__.py +0 -0
  321. /evalscope/benchmarks/{aigc/t2i → amc}/__init__.py +0 -0
  322. {tests/rag → evalscope/benchmarks/bfcl/v3}/__init__.py +0 -0
  323. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info}/entry_points.txt +0 -0
  324. {evalscope-1.0.0.dist-info → evalscope-1.2.0.dist-info/licenses}/LICENSE +0 -0
@@ -1,66 +1,71 @@
1
1
  evalscope/__init__.py,sha256=oivLvqwNw2JlB-h-Z8_525IpfKcYEkS51F59tEfpy5w,445
2
- evalscope/arguments.py,sha256=3mYv_kPerYxxI426GifY5mUmy8CSUaaFy7mdskPFKgY,5881
3
- evalscope/config.py,sha256=CRwJgcPnHp2mBmVA3IihsBrt6gGP0AIXqgBIwxIYAUM,8160
4
- evalscope/constants.py,sha256=mtKSLlr92e6c4ze0-FdZrNE1mp1VlFcE42KMD3DwnK8,3239
5
- evalscope/run.py,sha256=sksjcOsI1Q_0Jzgvs470_bkcKWA1zH6qJj_ZJgEGeMM,6281
2
+ evalscope/arguments.py,sha256=jKAF47PsqXRioU21gRHw9hxJnfR31z_X7c__glRY5ns,6257
3
+ evalscope/config.py,sha256=74sX1TH0OC6kSw9yedySfbcywVV6pXxna8DH-0_-hDA,11637
4
+ evalscope/constants.py,sha256=BRjknIG0NCuUK-040ZmrUsf7WRIHfObJgJ5ilJfPhAc,3791
5
+ evalscope/run.py,sha256=dKFesxZZteOhscHif2A8xQHsJnG78D-m2gdfaWyMNC4,6742
6
6
  evalscope/summarizer.py,sha256=HUDJ1zKi22uNst3AUfX67Z0sHzeZy-4S8sYyvxJnBzc,5901
7
- evalscope/version.py,sha256=OOygMFcZzcXVtNof6kBqsKsaK1Y03SJIHehdMdcqyT0,118
7
+ evalscope/version.py,sha256=qGtSETKmFUoaalidgoIBbZIYjbYTgLAapOQYohFtYxg,118
8
8
  evalscope/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
9
9
  evalscope/api/registry.py,sha256=Qk0KMGDbt-iI0-OfoJZbOtxt76qreAVWh36HOoQAKM4,5448
10
- evalscope/api/benchmark/__init__.py,sha256=PW--qkFb5b6DlKKNwhI873hXsaoP3IAgdHayQQYfKt8,147
11
- evalscope/api/benchmark/benchmark.py,sha256=OyQElOvIjeYw6BlYG6OZ9RqX1Gaz5f9Ka_JuUZPj-_A,9099
12
- evalscope/api/benchmark/meta.py,sha256=-zhwrUPbhFCI35ugE5jBhElpiZeSNZ8XP83pdgArqIc,4026
13
- evalscope/api/benchmark/adapters/__init__.py,sha256=qtjE9gXnx4SiITtEl2ii_IYoKBKXMVO7ntabexSXLD4,156
14
- evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=YtiPzjZ2IB4spvNwnJ9Lg7bTWjBXJjQ-7druKi5xlNc,27913
15
- evalscope/api/benchmark/adapters/multi_choice_adapter.py,sha256=wp_6Kws3GoBk_mSzQP8Nr40osFf3iPJpntkANYAuIcc,2979
16
- evalscope/api/benchmark/adapters/text2image_adapter.py,sha256=Q0G0VI8zaxggLO7Q0S6G0ZnK3nTwo7rngXqpaY_cVgo,6281
10
+ evalscope/api/benchmark/__init__.py,sha256=AFP3T_Pml-8LtT1ZaxVsrX_BCPXMw5ue7cfiBII-GrE,247
11
+ evalscope/api/benchmark/benchmark.py,sha256=pmb6Y6JRYDtkzBi5HTh2M64dkSabuXcemVg-WY7HdHo,11644
12
+ evalscope/api/benchmark/meta.py,sha256=SQ6b6wNSHN6BUCmr5Bdi3C-dFkgdCzZ_xnIjLmj3-y4,4302
13
+ evalscope/api/benchmark/adapters/__init__.py,sha256=XXER_DdSiz70t-I3w4CuMSeyxiOIRGzG8v3ZROs-o_g,340
14
+ evalscope/api/benchmark/adapters/agent_adapter.py,sha256=ecuvOayj9kRKuLaflbBDnFV3vibFxKkQw7a3fOvsYwI,234
15
+ evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=xGz92QS-ADKrMColnG1jHbtvEKYwzodTIX6YEJhoDaM,31171
16
+ evalscope/api/benchmark/adapters/image_edit_adapter.py,sha256=06V-_A8RKuMNYMt7-vaXn2qBa9LIZgfFO_6PUuhAkh0,3052
17
+ evalscope/api/benchmark/adapters/multi_choice_adapter.py,sha256=auqLNvF50Or9bo3LOmQLXHfFaTTCTqvQzZog3glInng,3062
18
+ evalscope/api/benchmark/adapters/ner_adapter.py,sha256=_rvfl8cNlvKoQkHqR2tC_K-xZaV0TsB_pIzI4sP_SM0,8906
19
+ evalscope/api/benchmark/adapters/text2image_adapter.py,sha256=jO64hwjQexIv-MTyHH0Ffp_6p--9TKufOmX_U39mAnE,6385
20
+ evalscope/api/benchmark/adapters/vision_language_adapter.py,sha256=5d7ITkeosikb7u0ag0WkMaZ0SAYGkR_wKM9NP495GKk,280
17
21
  evalscope/api/dataset/__init__.py,sha256=RHFMzwfONEqmmn3vRtxyN3r29mipDUUUSEDhuwm0YpQ,147
18
- evalscope/api/dataset/dataset.py,sha256=rqVQxnEKfNDGowSxTwV9HSDRtmjUfu4oCEIc_y1ExkY,11333
19
- evalscope/api/dataset/loader.py,sha256=7BHtxlV3smrV5R_RNifvMNmH9o_uSSKmngSM-ewDQ70,9668
22
+ evalscope/api/dataset/dataset.py,sha256=y-1DvPxN1Gxf-oEnrUq0Dcs4-rUQkApXP_rVYwsixSM,12119
23
+ evalscope/api/dataset/loader.py,sha256=44wQ3aBbn4YJyRjEsA1Bpg1DZicdCUzVybPoba_JhzY,9797
20
24
  evalscope/api/dataset/utils.py,sha256=3E0ikqr6QWV_lX0d3Z4F4xFuVTcwbeDPgCvJY7v83Bc,4935
21
25
  evalscope/api/evaluator/__init__.py,sha256=-Ure6X4GlE7VYSNWSZ_DpjbUBGa5irVTymLENEHTYqY,138
22
- evalscope/api/evaluator/cache.py,sha256=Hovka77enKYTxomeTnH-e1vPzozRiZ4CnHunHEWATiA,12546
23
- evalscope/api/evaluator/evaluator.py,sha256=SGW4RIKc79IlUP5FisrEycJlqORcaYxyIP5eabaSfeU,1600
24
- evalscope/api/evaluator/state.py,sha256=vLTrICWWqcK9asfPJFB0JfOGXZnVKmeLcvBACtvEfX4,8543
26
+ evalscope/api/evaluator/cache.py,sha256=xzQvLd2EzZOrWcHAauT-hdeRCkx6BqNIJ2rxvrMFMak,13370
27
+ evalscope/api/evaluator/evaluator.py,sha256=xMF4w2qiQ7NNgOhSKs9Vd4VZ33SCDwTTJ82lDhaj1FQ,1734
28
+ evalscope/api/evaluator/state.py,sha256=Elz2cmbvOOqvOaEOAMatxgk4BdjqDZB3XKTaL4iqJLI,9039
25
29
  evalscope/api/filter/__init__.py,sha256=5eWKjT-dAiz8nE0S6WnU6plqjXZHYn7CJOgFiHSoovM,66
26
30
  evalscope/api/filter/filter.py,sha256=fsPddaHE5wwFIXgUWITFqlYXqdh6vx3QqcEf3rSXKVI,2068
27
- evalscope/api/messages/__init__.py,sha256=31jIVA2zSwDgAcOdOd9pmj6-w-U27izxf2Pz-1cMvbk,352
28
- evalscope/api/messages/chat_message.py,sha256=XFalZ4e7Z-V3bbABMMsDvad0UiYcIz8kzrp3Muyzqfg,7698
31
+ evalscope/api/messages/__init__.py,sha256=UKZ9VVCt7NPrcZXv_1e8MZ8mOWu0eLRvMIXykpJPZ9I,378
32
+ evalscope/api/messages/chat_message.py,sha256=D88TklSAWOaG21EBDVDoRPwzVCqzEGbVW4sA8Af4axc,10053
29
33
  evalscope/api/messages/content.py,sha256=gUBUeK60BUhkwoulyzKL6q0iMt3VLlah9onLG1XVrWY,2772
30
34
  evalscope/api/messages/utils.py,sha256=uqlEbYEoUKpXLW8tQtP-cY5Miq7W0Xl6a98j55u6m6E,1266
31
- evalscope/api/metric/__init__.py,sha256=Cj2F8eiVny5uNtfPXKwQDq2owlHVKNzfr-COLYMEox4,106
32
- evalscope/api/metric/metric.py,sha256=XkjBqpZbFYynhTIH8WawfPmItbDQ6jWufE_ox9zDPCU,1568
33
- evalscope/api/metric/scorer.py,sha256=9IATvlJbp47b2iAn5KNO2v2tQIa1lqRlVaXWXce2iN8,3309
34
- evalscope/api/mixin/__init__.py,sha256=PagRD_Dz93Tsl-5YKQMZQAodx867Ow06P8uPQSBx4KM,89
35
- evalscope/api/mixin/dataset_mixin.py,sha256=ZJMcX3J4L0uNC_GkDwndSRjytxlbgldDeFIRfVCPCks,4395
36
- evalscope/api/mixin/llm_judge_mixin.py,sha256=KPNH41IL7md5XEYqC2ZbmnYm4tIrV-MgxpfKOWbYsMc,5624
35
+ evalscope/api/metric/__init__.py,sha256=dVKKjUMwda_p6T3MR0Hz9NwSzXM7WVwzrjEy_RE2xyM,123
36
+ evalscope/api/metric/metric.py,sha256=DWMxAmAu8aisad81FpubQCkdfDLOiBaQ3NIgfhDp9y0,1702
37
+ evalscope/api/metric/scorer.py,sha256=dczSQwkRmPk1uvNCMGT5G6nYbwWTcpwsZtyYXWkrJII,3749
38
+ evalscope/api/mixin/__init__.py,sha256=xBuoTuao5o_EFThgeeeWI87x64Q12aJttsaZc8gak_c,83
39
+ evalscope/api/mixin/llm_judge_mixin.py,sha256=ECVDfxCeAEkymFssD7xKhIDcct2qgQTqGnbijXk9leE,5675
40
+ evalscope/api/mixin/sandbox_mixin.py,sha256=RbTpZXr6ohxgp1vU4YGMKmGKiIzVqQZ44quAHBX8zvs,6539
37
41
  evalscope/api/model/__init__.py,sha256=YxKdz1IKUt6eYoC7nx81yD2BtyiWQDvaoTcc8O9lvoE,286
38
- evalscope/api/model/generate_config.py,sha256=QMOgi9PUhvdkHzuP5DdOWUX6dOUPh4lqJd1d-0w7XGE,7852
39
- evalscope/api/model/model.py,sha256=YjXI6rIGhaUZavhQ0O77XdCCMruNy-iSIehP8gPcN4k,12662
42
+ evalscope/api/model/generate_config.py,sha256=W5Yg8EyEMumIfpTGQMlZQ3D0p282pVIlhXGPj8sVQuA,8218
43
+ evalscope/api/model/model.py,sha256=c7YVbYYk47MHWwPjoB66xWjgmHdUGTOSOdtIsLcJfyc,12782
40
44
  evalscope/api/model/model_output.py,sha256=NeN6bLtAvg_3fTirewWfdP-_x4SJXa9pGuRpyXJY3B8,9333
41
45
  evalscope/api/tool/__init__.py,sha256=bEaW5ryY-erLcl2zMoDJNgiaBqlSPAL0jQ5daUHvvrw,272
42
46
  evalscope/api/tool/tool_call.py,sha256=WqMnw69L_yhQWycENZ7azPRhxRidhmrMcYAy7UTIqvg,2836
43
- evalscope/api/tool/tool_info.py,sha256=aqquWQRWWx7fPItIwiubiz2VRe2TLl_Jmn1ArIlngbw,5716
47
+ evalscope/api/tool/tool_info.py,sha256=FQOBqxKZ6Qb4f40iRH1mLg64cEhu1_-9Rn-f5iUrD2w,5733
44
48
  evalscope/api/tool/utils.py,sha256=IWFzM6WspzBmNPicXn6b7KS6Y-1I-ErsK9fua4cb53Y,2324
45
49
  evalscope/app/__init__.py,sha256=HWLXld_JXcBDsdL4L_4E8JsKyuBwwPUSwlejKnZ3HKc,579
46
- evalscope/app/app.py,sha256=8mSBp8qUCCmqupV4FEPMPdT9jL-bYu4DdH2qj8P0ktk,776
50
+ evalscope/app/app.py,sha256=EaBWorA87ZmyIHovIE3styHWEVFsu_F70pTmP4-5zTQ,836
47
51
  evalscope/app/arguments.py,sha256=1wHTLeFx1G94cKXYOeOVe_wTiOY2D929UctIRGOtRaQ,699
48
52
  evalscope/app/constants.py,sha256=oG6tZ618zJcCnwZ5THnYL0gWTPDb5XKrnmdrWxY3Z4Q,385
49
53
  evalscope/app/ui/__init__.py,sha256=IBxyQ2H-kSHoHJmXWDR8QMermvsMbiu673PQbXP_FnE,616
50
54
  evalscope/app/ui/app_ui.py,sha256=wLrQ4VM7BnzvaYmPAk8NH9t5BaWooHFJcgmAOOd2I1w,2032
51
- evalscope/app/ui/multi_model.py,sha256=fO8z-ZFucWtgaKmuQ50AkUp4BoYOFqOkxeTBUUAK0bM,15122
55
+ evalscope/app/ui/multi_model.py,sha256=mvMgpgiJGRrNRtReFcD_PiLatq-81zp65Vb3JYUP3PE,15356
52
56
  evalscope/app/ui/sidebar.py,sha256=JA0QbG2iPStK-lFy6x_AjOHlQdesmgXoS0OYJUJ_Wyg,1339
53
- evalscope/app/ui/single_model.py,sha256=7HjfmufZm7wXNtT-ZKnQ4PgX-I_tX5og-s30leX_Xr4,9487
57
+ evalscope/app/ui/single_model.py,sha256=zFt1uDYrcgNJ7e_YLigrs6IXT3jyGMVn-7rv4CHAZvE,9741
54
58
  evalscope/app/ui/visualization.py,sha256=jXFX_-7woQkcAiQkPAIRwVv1kdRdXonn9IvmB8yzPDU,1102
55
- evalscope/app/utils/data_utils.py,sha256=H4XYWgynmkY0ENU6FFSmrgse3aq3Is11jRRf-_nCvKw,7408
59
+ evalscope/app/utils/data_utils.py,sha256=GYOfkh0NoueeX3od-L852Q9C9SSkEFlW_40wjPa5b9w,7470
60
+ evalscope/app/utils/env_utils.py,sha256=2pmz4uNun-XNP6TqM6Oe576XopweEClhBaIdWO--kd0,382
56
61
  evalscope/app/utils/localization.py,sha256=rWEviBmcnhIpAA-cG8djbbUA6p1Y358c0dxge5Pqi1U,6131
57
- evalscope/app/utils/text_utils.py,sha256=lZy-sXccv24KyjvOGpZSQYMfM4XSKz3qcriOhsiYAdY,3499
58
- evalscope/app/utils/visualization.py,sha256=dwEXbGfY7vFysnL0HmrHS2BEWaJkg-dZ9ayDlRhdvv4,3559
62
+ evalscope/app/utils/text_utils.py,sha256=-K-hRPMZ29Yqjhzd-391gPaD4B4wUuIg71PfbLnGJ38,3754
63
+ evalscope/app/utils/visualization.py,sha256=lycwcr-kFT2FKVw6iWMh3iD_n4dqpWVzhXMLDnkN8QY,3563
59
64
  evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
60
65
  evalscope/backend/base.py,sha256=qYu8Shokrtrx-N6T_BAJk_6OCpovUBYuN0p3wngt-dw,1030
61
66
  evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
62
67
  evalscope/backend/opencompass/api_meta_template.py,sha256=OGH0lGJmBFKHs-6u6RPCov13_ArO63E6pV-aX1WVljU,1707
63
- evalscope/backend/opencompass/backend_manager.py,sha256=fxTERjtndDoxfjFDxULYc1XZ24lY9HNkNLsmqhkpZtw,10500
68
+ evalscope/backend/opencompass/backend_manager.py,sha256=q_5ABnnJb14T2L2bKY2y-ErJ9K4_65Rpl0a-h3hZ4TM,10337
64
69
  evalscope/backend/opencompass/tasks/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
65
70
  evalscope/backend/opencompass/tasks/eval_api.py,sha256=ZaGdUbEOtAW5VX3ZXmpHIttg_QrID34EnBTylD3uvos,1152
66
71
  evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=JHSq4EnPJgv4sRJJplLH80EqE3ghtkn2k8HnV6DaDew,5406
@@ -99,33 +104,32 @@ evalscope/backend/rag_eval/ragas/tasks/testset_generation.py,sha256=XMWW8ucN7ojR
99
104
  evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py,sha256=dZAjsfiR839INO3nbb9psLn-eL4sZOzpU6JMdtJUXtw,1895
100
105
  evalscope/backend/rag_eval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
101
106
  evalscope/backend/rag_eval/utils/clip.py,sha256=GLHhPCac2AH35AvRLvVqePA1gIMAewHTFmCJCDZzvqU,5015
102
- evalscope/backend/rag_eval/utils/embedding.py,sha256=QR9ewFMTV35JEWl0nCw4gWxlg8UodosMxRTH-JghMJY,9388
107
+ evalscope/backend/rag_eval/utils/embedding.py,sha256=nuwBsiXPAwZisEmg3V4fWekd2tqp5mWRVb_fxNB1zTg,9867
103
108
  evalscope/backend/rag_eval/utils/llm.py,sha256=1OH-985iIDtCOlCtzGmHu6GT_l1vJe7Iv-WyltQbcSc,2451
104
109
  evalscope/backend/rag_eval/utils/tools.py,sha256=FU7tNu-8y8V_o_kArFVTTLM_GzL12KBNeXiwQw5SpJA,1529
105
110
  evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4tycyy-FJgzLdjeY,84
106
111
  evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=jlwM13Ty-Ax6AeMsNlo9xIBupNFgnceYuXtCmh0hNTQ,6160
107
112
  evalscope/benchmarks/__init__.py,sha256=WHR4ej9Tqa2N9CyIaUWXS8EnHZtcujaNeg9hf8GT31Y,1182
108
- evalscope/benchmarks/aigc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
109
- evalscope/benchmarks/aigc/i2i/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
110
- evalscope/benchmarks/aigc/i2i/general_i2i_adapter.py,sha256=QOen4eJ1wE_KOrXk-JDDifDbn6ulqLTgVC61a3TSEYA,1665
111
- evalscope/benchmarks/aigc/t2i/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
112
- evalscope/benchmarks/aigc/t2i/evalmuse_adapter.py,sha256=3kRMglG82RXRiA-Hucj7o_O4hrrDaqJxExbmyohANQE,2898
113
- evalscope/benchmarks/aigc/t2i/genai_bench_adapter.py,sha256=CkJFoQJzF5tR46hr0X0Wu1VJ57uBr28BiUr3WT-5X2c,1840
114
- evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py,sha256=nOZ8Lk_sRNiPK-d4a6hdmZ8mM40uIvpu5vlLF8Mb44s,1341
115
- evalscope/benchmarks/aigc/t2i/hpdv2_adapter.py,sha256=Pr2_YW31-DIiklSkR5bGuwEBQWyBQleRiRAR7L7MoH4,1460
116
- evalscope/benchmarks/aigc/t2i/tifa_adapter.py,sha256=OuOO-txcE5ZQHRZj78XGUOBfxJoPZpL3K0k_P9X4kL4,752
113
+ evalscope/benchmarks/aa_lcr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
114
+ evalscope/benchmarks/aa_lcr/aa_lcr_adapter.py,sha256=7KZRdIhg733vBMBWngxTjtrZtl_DHjwMNLt9C2tN0_w,7483
115
+ evalscope/benchmarks/ai2d/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
116
+ evalscope/benchmarks/ai2d/ai2d_adapter.py,sha256=qnQT2E0ZG8g4noOafu-QvBOKm-zEJ5X08QHw3ekNa4w,2473
117
117
  evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
118
- evalscope/benchmarks/aime/aime24_adapter.py,sha256=HTlriHoHzlm1Rf3KAiGRLs8sx6Gyf6s7RGtOjk_hGS4,1767
119
- evalscope/benchmarks/aime/aime25_adapter.py,sha256=ZOE_6Zhg1MatWJSu2Zq372nKUODYtNFZimS1MJRFz5A,1591
118
+ evalscope/benchmarks/aime/aime24_adapter.py,sha256=UGS0DhfylTbhyOfnOGKwDiXW0lMd47EPeMtY-WNPht0,1935
119
+ evalscope/benchmarks/aime/aime25_adapter.py,sha256=W2Jf68G8-QSgbZxgPJvCBq1VbQ-wRbeH1u9Qb2WNZkA,5157
120
+ evalscope/benchmarks/aime/grader.py,sha256=7qi3aFY6F-o70H3zRH_QHrXmPQz0euAhJaw_IATiw8k,9259
121
+ evalscope/benchmarks/aime/math_normalize.py,sha256=--ax2mPVb2jXtfk8__K0OYKit3HiDqKOFEcOSSX9SA4,5830
120
122
  evalscope/benchmarks/alpaca_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
121
123
  evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=sjaWcK8WH1XY0kzm5eHsq_7J62EJocAf4gRV_UB8ZBE,4971
124
+ evalscope/benchmarks/amc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
125
+ evalscope/benchmarks/amc/amc_adapter.py,sha256=ame7mUbcXx1gvIVaqdv0HyBNZEaUYn3Amy06mO_sMos,1586
122
126
  evalscope/benchmarks/arc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
123
127
  evalscope/benchmarks/arc/arc_adapter.py,sha256=GASZmoJ-PpzBG70cBdABZA5uVqoyosjV-jf9WShK7L8,1622
124
128
  evalscope/benchmarks/arena_hard/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
125
- evalscope/benchmarks/arena_hard/arena_hard_adapter.py,sha256=Ddn_hVO1PvNQ_kNknXfdJCz1AVnXZEdGWq4gX1_Qqow,7275
129
+ evalscope/benchmarks/arena_hard/arena_hard_adapter.py,sha256=1XNzbu12FIupWgVlruaOQZ4TGj_Tkg8xgYaqQ4q3H0M,7302
126
130
  evalscope/benchmarks/arena_hard/utils.py,sha256=23xCd7_ksrM4xMJBp7N2ZwpUpq1zpoQFjLm1oBcdgQY,5559
127
131
  evalscope/benchmarks/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
128
- evalscope/benchmarks/bbh/bbh_adapter.py,sha256=GcvgwBhIw7OG-ljWQ_urVOoWlrFjrBy1LAZ-Atm02Dw,5570
132
+ evalscope/benchmarks/bbh/bbh_adapter.py,sha256=lRI-DfdFkyg4ylW4d-6CUfiNqlF7K_IoTjzJz3jYTUs,6346
129
133
  evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt,sha256=xnzlaIRyeGlogG49v8nt4vpJO40J06ev4yc8cv0VSRY,1781
130
134
  evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt,sha256=sfo-2iOeVzB0OGgd7NSQFELTGDTsr2DQ3u-g0ivI-sM,3653
131
135
  evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt,sha256=UJBsc3Mwz8TZngdWH_NFlhhNbLhNHK6FvW9FHcS8H5g,1167
@@ -154,120 +158,273 @@ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt
154
158
  evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt,sha256=s_x6u5MLeKpuAHZj3GNQqY1I8vWqQIfJasOp9XcM7Ck,2945
155
159
  evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt,sha256=qfTZafCzNiz9ULBaDlfy_LISL617NyH5Nc0-nO0K0LE,2164
156
160
  evalscope/benchmarks/bfcl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
157
- evalscope/benchmarks/bfcl/bfcl_adapter.py,sha256=FH1y0ROEypq9beIX41FVzBS7zcCl_qUTxcG0N0lYiV4,11092
158
- evalscope/benchmarks/bfcl/generation.py,sha256=kf4BrNC24nHkwVysxJPUiFU55pUkev-7y5Op2Ws8GyI,8704
161
+ evalscope/benchmarks/bfcl/v3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
162
+ evalscope/benchmarks/bfcl/v3/bfcl_v3_adapter.py,sha256=ILOSPo9GR2BQAz-RrzptKGvCNs9HeW2YRUa0e-r1hPU,17509
163
+ evalscope/benchmarks/bfcl/v3/generation.py,sha256=c6lNjo-VTSUrVg-pqyPSucrbCKBOdBSyN0aR5AAtE4A,8701
164
+ evalscope/benchmarks/bfcl/v3/utils.py,sha256=X1nfKmXp_dKUoYb4BzNN0-EwArE0Ppfi6m0mYB7ccLc,859
165
+ evalscope/benchmarks/bfcl/v4/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
166
+ evalscope/benchmarks/bfcl/v4/bfcl_v4_adapter.py,sha256=hJWOT7WtgxuwKT_AmtAF3h25JnvYYXbDR1WWnyQOE9w,8974
167
+ evalscope/benchmarks/bfcl/v4/utils.py,sha256=bQInR19wJFPIOiRGjrJc3bGWWkJbL7zHwj3RdSavB5Q,15142
168
+ evalscope/benchmarks/biomix_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
169
+ evalscope/benchmarks/biomix_qa/biomix_qa_adapter.py,sha256=rHid3tPEfauB_Q5pF3mMoyuyV01SHyBJEXm-7A2HV24,1218
170
+ evalscope/benchmarks/blink/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
171
+ evalscope/benchmarks/blink/blink_adapter.py,sha256=ocQKsDGwnUAg2si2p7tqIGeH3PKPqTSByjbt7ceraRo,2642
159
172
  evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
160
- evalscope/benchmarks/ceval/ceval_adapter.py,sha256=j1WkDrEUiNo6MOu-Kt3NzD9DBgye20JMbMTlQMQw39o,8560
173
+ evalscope/benchmarks/ceval/ceval_adapter.py,sha256=4FLPgY-UtqINafnNxfOsE9AwS6GFXFCUGOBI-4EZUGk,8503
174
+ evalscope/benchmarks/chartqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
175
+ evalscope/benchmarks/chartqa/chartqa_adapter.py,sha256=DA1kthMUvn4_GUfdRfuR-au3RkhE3WKPnR_f8nlhd4c,2813
176
+ evalscope/benchmarks/chartqa/utils.py,sha256=Ta9ZUMpIqzrAszju7_WOMBAlilH1Tx6TCheVpjrZJJI,1672
161
177
  evalscope/benchmarks/chinese_simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
162
178
  evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=OWzRlSGswV24V-heLqqo7GQzpJp01TZ0DhFHq0iUP9A,8238
163
179
  evalscope/benchmarks/cmmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
164
180
  evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=P0VPAL5T2V_zj0q7im0FdDoq_W5rinorwN5FRYaFFUI,5377
181
+ evalscope/benchmarks/coin_flip/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
182
+ evalscope/benchmarks/coin_flip/coin_flip_adapter.py,sha256=qHg0kN4SX5cT_3cyFg0wfN69ldIEivyZTTX1A6j7LD8,4687
183
+ evalscope/benchmarks/commonsense_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
184
+ evalscope/benchmarks/commonsense_qa/commonsense_qa_adapter.py,sha256=Y1c13U5D4x9oNTQ5F3ve2_3Ia1fkQXiqcf3ESODT4HQ,1109
165
185
  evalscope/benchmarks/competition_math/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
166
- evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=NOqckeyuabH_nwaxL5IWmH887UO5rvBKA2jx7qb9fNs,2226
186
+ evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=0zOsMwl1mNGDzOEQqsISa6GcwliPtWz0EBEHm3TR-AI,2394
167
187
  evalscope/benchmarks/data_collection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
168
- evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=Ut5sIcTiJQGaFEgE7gM9q3bsDeFKXg_2sDzxcOqchsE,8451
188
+ evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=PbV5S0rUVF0jgrBKNjuZh2oE1FAsbYnPymg5u7NBjqo,8712
169
189
  evalscope/benchmarks/docmath/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
170
190
  evalscope/benchmarks/docmath/docmath_adapter.py,sha256=-mel6hA-x_e7fV0uOHdX5BpoQEVyQ5VqwIwEqSNDpnc,4623
171
191
  evalscope/benchmarks/docmath/utils.py,sha256=d6Yjoa5q91kjr1SdVPVBndzDaUzMlO_GfEqMtUXXr0s,7707
192
+ evalscope/benchmarks/docvqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
193
+ evalscope/benchmarks/docvqa/docvqa_adapter.py,sha256=xGaayycILYoLd8r6wLLppDbU6Z1FdafbYFyjLHaftAA,2882
194
+ evalscope/benchmarks/drivelology/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
195
+ evalscope/benchmarks/drivelology/drivelology_binary_adapter.py,sha256=_wqS0h4qQBeGBx9W_KbtO_tfzpxXsM-jejI0TK_i0io,7005
196
+ evalscope/benchmarks/drivelology/drivelology_multilabel_adapter.py,sha256=fnPPFma-fTRe5B3n_1ObN5wS_jY1QvCA9mcovAMR4ss,11735
197
+ evalscope/benchmarks/drivelology/drivelology_selection_adapter.py,sha256=dUTs0Dqc-54haam478Y0UkiFoDH7YgKfQE-5vxk99NU,1655
198
+ evalscope/benchmarks/drivelology/drivelology_writing_adapter.py,sha256=6-DZxTlDGIJ8iM-egu29RlpGApNjUouv6jD11PVXU3U,8026
172
199
  evalscope/benchmarks/drop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
173
- evalscope/benchmarks/drop/drop_adapter.py,sha256=PyvZ1WOdHQ0u0_JpuP97_yQsCUbzGcYsJf3bWKbakzg,9968
174
- evalscope/benchmarks/drop/utils.py,sha256=Z9PHrNnRfGqFHCLONg5SWKARp1eTJlHFc_bU46t_YrM,1344
200
+ evalscope/benchmarks/drop/drop_adapter.py,sha256=Vl6IgFtK3zIUujlrjcCI7oVLlvpaRanDcDDSTWNbDfU,8851
201
+ evalscope/benchmarks/drop/utils.py,sha256=zdT31cqVp6gzIcOxsxsqfTn97SZnTuM3vuvLls5VJWY,4878
175
202
  evalscope/benchmarks/frames/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
176
- evalscope/benchmarks/frames/frames_adapter.py,sha256=hqFBJsf6fxwDmkE0ZQnkELiEP0dp2cUodKn7kUbTuqM,5479
203
+ evalscope/benchmarks/frames/frames_adapter.py,sha256=w1kRya7w5omt95HHE6AzbzYVhyTT5r521676d_xJ6Vg,5514
177
204
  evalscope/benchmarks/frames/utils.py,sha256=gULWM6Rwv5bTSSWcDYp-iSIoWj8r5VtbQakhRzHJq8A,1172
178
205
  evalscope/benchmarks/general_arena/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
179
- evalscope/benchmarks/general_arena/general_arena_adapter.py,sha256=UkIjxPSr-qbrloNf2KhDhZClvnes7qP7Bcu1XTXxsKU,21553
180
- evalscope/benchmarks/general_arena/utils.py,sha256=zS4l1RKwvl0Z9Mk7kth9WVQGHTgE_aNDZa_XNy9tGyM,6874
206
+ evalscope/benchmarks/general_arena/general_arena_adapter.py,sha256=0qydHMwVaD7bzyK2Mccv9m4JnOfSy2vE8g1YPOaWSg0,21663
207
+ evalscope/benchmarks/general_arena/utils.py,sha256=p6pZfvdNCMOU_vWHm_DYU57Sa2WTDdFOkVBubblCRN4,6912
181
208
  evalscope/benchmarks/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
182
- evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=7VKg_EzXkRvoWpR7h8qB4sVVb1eZHCGcPk-X_NMS5tE,2062
209
+ evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=p7_C0CmKJthMY1Iri1SyNfssuYBws_dkhPMREu-uM94,2059
183
210
  evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
184
- evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=u29IsH5sgw-T0IezuI1jErGwykz-F7875AdEhdvS5rk,3522
211
+ evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=_7Jk_h-qcaxWHgrULojNqXwZ8XgicmXhYT8bOKwnyAU,3519
185
212
  evalscope/benchmarks/gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
186
213
  evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=zWK2hhyKw5n8K30YvMjSm6XMwyrireODGTE6wKmyuOo,3311
187
214
  evalscope/benchmarks/gpqa/prompt.py,sha256=b1Gw2D5dEdhvLYymPfcvGKJdHrIzpiZkOwURKSxiQJg,5576
188
215
  evalscope/benchmarks/gsm8k/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
189
- evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=W4vTXsC7iHN1AgvpaCf1Rj7y2O8QczIluucnpSC5aYo,2636
216
+ evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=s0ytoqydH3FEG0KALrIlYXOLBKSrC7ikh0r8_v2dKGM,3579
217
+ evalscope/benchmarks/hallusion_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
218
+ evalscope/benchmarks/hallusion_bench/hallusion_bench_adapter.py,sha256=LOnO1mvUJxU87-bZBC8qYtwlmFn3So2Yo9I3CkDjtIg,6544
219
+ evalscope/benchmarks/halu_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
220
+ evalscope/benchmarks/halu_eval/halu_eval_adapter.py,sha256=4bdzOEyOjxbTng9U94Yscknc7eeJSFyVf_ifZtTqYnM,5332
221
+ evalscope/benchmarks/halu_eval/halu_eval_instructions.py,sha256=z0_1rx3PqQHbheiUpUAdp4aUP6oBMMAEAIvDmWND07w,9770
222
+ evalscope/benchmarks/healthbench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
223
+ evalscope/benchmarks/healthbench/healthbench_adapter.py,sha256=gm5LOR5J1E3eXQ9aWF-rif2_l7Khx9UwS1Dfg-oEx8E,13242
224
+ evalscope/benchmarks/healthbench/utils.py,sha256=M8SnOEhlqXWm03CFE6CAtbMiu6MqdGgVczAv-LPjA7Y,3683
190
225
  evalscope/benchmarks/hellaswag/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
191
226
  evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=tAe63NfV5ljUm1f4RTSFxWOVKBUhk3Cc0EGzF5uYLK4,2041
192
227
  evalscope/benchmarks/hle/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
193
- evalscope/benchmarks/hle/hle_adapter.py,sha256=4YVmETL9mEiLxF4vWRjePLyFaxelax6nOaqoAH5ZxmU,6389
228
+ evalscope/benchmarks/hle/hle_adapter.py,sha256=kJP7bzIDbr82GKi0FTy2zf_j1UWNBfuXYzokYJ-S9WE,6410
194
229
  evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
195
- evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=5x2pnkbI9ZPPOyrRBsJ5ZcOCGJr8OR7qXLgVlY6eJxs,5825
230
+ evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=KhJ91yqr964FccHIDE9A_nTldfhhLTzVB4Cpv3RDN5I,3933
231
+ evalscope/benchmarks/humaneval/utils.py,sha256=rPnc_JuSjNg9aV7UMUwsLrDlm-ufj64GNIBCWBeuRcM,6517
196
232
  evalscope/benchmarks/ifeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
197
233
  evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=55FQwJ0_eDijppkVVlM5XCXzgRFmjH1SvGMItGsvn6o,2769
198
234
  evalscope/benchmarks/ifeval/instructions.py,sha256=HXnn1JgU3dpYltqIovFAn02DxkYOGw337kLMlOfJxJE,56048
199
235
  evalscope/benchmarks/ifeval/instructions_registry.py,sha256=3UXzVLgKwk_cf-2aG2tozjqYgvqm5Mj3ZRRb8rI-ucU,7262
200
- evalscope/benchmarks/ifeval/instructions_util.py,sha256=vkemXeylJMmgW8LgfQe4cSy2OF-oH_NcSZtzyZDURW4,25780
236
+ evalscope/benchmarks/ifeval/instructions_util.py,sha256=Zl9Q6xwtZtIkXLoVwz7oifSEyvbDGETljKHgc4tk6TM,25730
201
237
  evalscope/benchmarks/ifeval/utils.py,sha256=MQt-b4K6uqU9H5TAM6Gxyz46r6XRBOgDsgdnwB0veg0,4470
238
+ evalscope/benchmarks/image_edit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
239
+ evalscope/benchmarks/image_edit/gedit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
240
+ evalscope/benchmarks/image_edit/gedit/gedit_adapter.py,sha256=a6hhRbnGCvMEMsbnSbczjXd4vHfMVEnFfP459FCF_Mc,5250
241
+ evalscope/benchmarks/image_edit/gedit/utils.py,sha256=UN0z9Dafs8d8lEXqxin321d8smiS3H9p3gyLkZFPFNg,14735
242
+ evalscope/benchmarks/image_edit/gedit/vie_prompts.py,sha256=qVXWQyVUwZxEasDjVmYBk30_JI4gnvHacMOmMsA4wcI,22056
243
+ evalscope/benchmarks/infovqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
244
+ evalscope/benchmarks/infovqa/infovqa_adapter.py,sha256=3m_EvfRZ5ItHkz-3mVlsF_NnPS7NH1-EXwUW-s4VMxA,2617
202
245
  evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
203
246
  evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=mNHA_Fuj_gAdOEoR7oChnGmErf1czqwnk8Zk-jRhBys,1304
204
247
  evalscope/benchmarks/live_code_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
205
- evalscope/benchmarks/live_code_bench/evaluate_utils.py,sha256=wgx8RDbkXi2Mlt-aK_6o4VcoPb7I3eL8z8h8JW4SnEo,6510
248
+ evalscope/benchmarks/live_code_bench/evaluate_utils.py,sha256=maN8qHmDHJpexPeB0qwZoXJ5zrqPbJDYVRptqvXI9d4,6827
206
249
  evalscope/benchmarks/live_code_bench/extract_utils.py,sha256=ZcQ8y741uawPo6I_1_XglR3eqJFDNrqc8fILKZupVRs,2375
207
- evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py,sha256=tl7nGLDUgmNtyR4faE0aoW11OgLhsx7ZdKmONGDlQnQ,5203
250
+ evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py,sha256=iJzmge-txK86lPn9mQbVlA7CPWXR4MpVdEDCfckkNRU,6236
208
251
  evalscope/benchmarks/live_code_bench/load_utils.py,sha256=fEzWz_fUGwi5Ncum5PNVF9jFcuDwGgs7Vt_10YKBE2Q,2087
209
252
  evalscope/benchmarks/live_code_bench/pass_k_utils.py,sha256=Ktrp_lXdfFzoHtQNQNdGfIl26ySjaPCHm4Zv-dFvRqM,2024
210
253
  evalscope/benchmarks/live_code_bench/prompts.py,sha256=P4KILIAIDT1MKDck0xHYV_6v9820wDZRhxVMazmlL-g,12600
254
+ evalscope/benchmarks/live_code_bench/sandbox_evaluate_utils.py,sha256=7DDx46EwtoR776vWjofJl1zaYCLdmeq8cF3fhDGdZgA,7424
211
255
  evalscope/benchmarks/live_code_bench/testing_util.py,sha256=TuoOTciC-hz3FTeDzsQB_THH3Be9UOP2XMrax-4sXkM,17282
256
+ evalscope/benchmarks/logi_qa/__int__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
257
+ evalscope/benchmarks/logi_qa/logi_qa_adapter.py,sha256=LmmG1gI8AOCpV-35_WdiZ_9Ges-pTufWEzbgrOUW3Go,1271
212
258
  evalscope/benchmarks/maritime_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
213
259
  evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py,sha256=Rx7iZ5JaEo73YwIzhm78gMDQ6gqcErbnWWXHxXM6BcU,2379
214
260
  evalscope/benchmarks/math_500/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
215
- evalscope/benchmarks/math_500/math_500_adapter.py,sha256=uuxjmqftY_r-hJBCjfBgYUELrBaB86MG8dIu2wTikgI,1848
261
+ evalscope/benchmarks/math_500/math_500_adapter.py,sha256=vPWqytzbJayhuJjh9Wv9gq44tkwrDehMmtPFx7QXYvs,1970
262
+ evalscope/benchmarks/math_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
263
+ evalscope/benchmarks/math_qa/math_qa_adapter.py,sha256=R0u0tiknCtxzMPEksstCDPT_M71pL2SxoF_KAEMxf7A,1170
264
+ evalscope/benchmarks/math_verse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
265
+ evalscope/benchmarks/math_verse/math_verse_adapter.py,sha256=Z4b2e3vCnllbhb457xJ6HJ6urfqfW3mHD9ZSumoEjQA,4321
266
+ evalscope/benchmarks/math_vision/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
267
+ evalscope/benchmarks/math_vision/math_vision_adapter.py,sha256=LEM5Zs8cqQpqeNaRW0CzHRPPMGu4NHrkjl-EgP4RHaU,4643
268
+ evalscope/benchmarks/math_vista/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
269
+ evalscope/benchmarks/math_vista/math_vista_adapter.py,sha256=yHz8kVPp0fkfL6n3lcPkdhOFrXsR2mOEA1oUoTFiwJs,5096
270
+ evalscope/benchmarks/med_mcqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
271
+ evalscope/benchmarks/med_mcqa/med_mcqa_adapter.py,sha256=oR2463a1kLAfBZOPA5gLOp2C6qx1cu2vKCutXZsoQys,1090
272
+ evalscope/benchmarks/minerva_math/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
273
+ evalscope/benchmarks/minerva_math/minerva_math_adapter.py,sha256=YaMT--hbOmlNlK5Q7iQ7c5XWVhLf3isVipeexOvrUOE,1823
274
+ evalscope/benchmarks/mm_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
275
+ evalscope/benchmarks/mm_bench/mm_bench_adapter.py,sha256=ht2DVt_zEBJp4jvGy3myHHgdUUP9eff2O5BpIc9Fv74,4376
276
+ evalscope/benchmarks/mm_star/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
277
+ evalscope/benchmarks/mm_star/mm_star_adapter.py,sha256=oamLv6U2-JAK5mdVLkUgYxkOahxQkQYMRKAyu_xPAUE,2818
216
278
  evalscope/benchmarks/mmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
217
279
  evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=2NT3QbfPzajUTFZ0tBCl6PRrtFtAr5jPZNQRW2Idlno,5947
218
280
  evalscope/benchmarks/mmlu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
219
- evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=GtIyUubUg6Q6Ydh1Adj0-32OdiwcsF-u-NQ0U-4AnQA,3891
281
+ evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=LTNNWREOc4HQ-A1_x5lItdZbzEvUCy77zkp7ZAh0hlY,3890
220
282
  evalscope/benchmarks/mmlu_redux/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
221
283
  evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py,sha256=m_37OIFrJB4ZIvtbDJ_m9P9mA2QtrNjGfbbVo15awJg,7402
284
+ evalscope/benchmarks/mmmu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
285
+ evalscope/benchmarks/mmmu/mmmu_adapter.py,sha256=WrykWq8n61CVrQ4XQhI3iEySgErHdZyng3udOL-Pddk,6054
286
+ evalscope/benchmarks/mmmu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
287
+ evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py,sha256=banPS1nDt9bQ95urKbSZnR-hBTw23eL9MSrHt_0ZLp0,4725
288
+ evalscope/benchmarks/mri_mcqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
289
+ evalscope/benchmarks/mri_mcqa/mri_mcqa_adapter.py,sha256=OJnJDo_yLZihYXeAIyPQo9fMAgcAfSqEPpfhHpxvtXY,1095
290
+ evalscope/benchmarks/multi_if/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
291
+ evalscope/benchmarks/multi_if/ifeval.py,sha256=7y2rnJ4q1_DVA7I9mUnF7TBpu7Kez0X_Xhl-AJInzWk,87949
292
+ evalscope/benchmarks/multi_if/metrics.py,sha256=LWnhQw25cRNMReJ_xJ7Fx7WYHcT9i2FG1FUjYOuQDrI,4291
293
+ evalscope/benchmarks/multi_if/multi_if_adapter.py,sha256=I3_YPPUuRbrs9Gt3Qjhx9RM5Vu2gDFnheDcGu-oe840,5924
294
+ evalscope/benchmarks/music_trivia/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
295
+ evalscope/benchmarks/music_trivia/music_trivia_adapter.py,sha256=zxJuNfCEQ2yU6OivAzrdhVSGcwPuu9dygho4VzELyZg,1281
222
296
  evalscope/benchmarks/musr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
223
297
  evalscope/benchmarks/musr/musr_adapter.py,sha256=kx6bckj7Nijl4Wysuj-mKYdy0hIRDJho8yVTup403Hc,1473
224
298
  evalscope/benchmarks/needle_haystack/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
225
- evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py,sha256=GRJrJ7O0OZlIMH-FyghcA54xNfBSYjPd-0TgtMw7vHA,17048
299
+ evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py,sha256=aQw8Sss1-ZgQPWqwMITOpAtwzMoYWDGjLhUpZtkcrvY,17030
226
300
  evalscope/benchmarks/needle_haystack/utils.py,sha256=k8WDigqt5LgzHw6DtaYsLtb3BJL0FTZS9JOyJCpoPq8,2935
301
+ evalscope/benchmarks/ner/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
302
+ evalscope/benchmarks/ner/broad_twitter_corpus_adapter.py,sha256=zA4K2LuEtu5MV7yJ8ClJ8kttFqcyO82KBpt6SornYWs,2012
303
+ evalscope/benchmarks/ner/conll2003_adapter.py,sha256=r_6UmR68ohFsn021zArkGRq0tRZSaIy9RNNJncag0i8,1970
304
+ evalscope/benchmarks/ner/copious_adapter.py,sha256=ufxsmTvEEayLaDJcUW5--oo6vkDY69W2yQ1fpD0E5lQ,3751
305
+ evalscope/benchmarks/ner/cross_ner_adapter.py,sha256=8UHFvZxKEghk30JZgvWbYFXnRBna5PHwI8_WZXpmCfg,4916
306
+ evalscope/benchmarks/ner/genia_ner_adapter.py,sha256=WHTSRj8PFvm19F1iqnujZ4qySIQ0rV7tiI-3HxuV75s,2457
307
+ evalscope/benchmarks/ner/harvey_ner_adapter.py,sha256=UVqpPNbTeWo_UgJm4f8xxOq1umXyOWb4pCz7s1ZxJpg,2098
308
+ evalscope/benchmarks/ner/mit_movie_trivia_adapter.py,sha256=jOldqrPdrFDSvs8ajidwK-c4zktclKu7KgLfHXBH-nk,3017
309
+ evalscope/benchmarks/ner/mit_restaurant_adapter.py,sha256=wUJBLGH992pbeKhb-e8ywC0XVvTGMiAPKjUxrpg9Iqo,2528
310
+ evalscope/benchmarks/ner/ontonotes5_adapter.py,sha256=oulC4XkVF42yjXWPuKg_zptLQiRItCmlZBlHN0shr6A,3546
311
+ evalscope/benchmarks/ner/wnut2017_adapter.py,sha256=uGrfp-4wYIcpEL9PqQx82uzCeWz6vIPKb7JlStTSE9M,2379
312
+ evalscope/benchmarks/ner/cross_ner_entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
313
+ evalscope/benchmarks/ner/cross_ner_entities/ai.py,sha256=RcgzYCygBmyrSOLacxxUN4cUznBZ3NemwfSR4hYBVKs,2484
314
+ evalscope/benchmarks/ner/cross_ner_entities/literature.py,sha256=ETzhu4PmiKS88NRkKPh96J9KiXKFdeQk5s_LSNqbD-M,1874
315
+ evalscope/benchmarks/ner/cross_ner_entities/music.py,sha256=_aJyKo83pO-j_LtGwXgrg9p8H1sHqXGPNW-wv1EIfWc,1999
316
+ evalscope/benchmarks/ner/cross_ner_entities/politics.py,sha256=taAqCnGdxHZGHM7sV0KONim8GjqVBrpMME6CVHwfJMo,1635
317
+ evalscope/benchmarks/ner/cross_ner_entities/science.py,sha256=DVZrCuMQ6-sPvRNTfx8iF_x9LaEBZ4o_RIWZADYKYGE,2919
318
+ evalscope/benchmarks/ocr_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
319
+ evalscope/benchmarks/ocr_bench/ocr_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
320
+ evalscope/benchmarks/ocr_bench/ocr_bench/ocr_bench_adapter.py,sha256=gkQb7g0-Lf5Sjemqs5kqogCLGFJI6YQv8-vGI1EbyLE,4392
321
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/IoUscore_metric.py,sha256=cBpRDJvI9f6vKRD4wTPv-8ThGddR3EhVobgjQQUAYlE,2606
322
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/TEDS_metric.py,sha256=31bL0V32Fq7prF1WoVjXmrmMdhg0qNcoiOaKykKOrZM,36528
323
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
324
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/ocr_bench_v2_adapter.py,sha256=QGY4R75UxDafIwSaOEPPuCaX3Z8BGoZVvcc6OWbeO9w,7976
325
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/page_ocr_metric.py,sha256=d1nU7LNwubBd_1rIe7i67hOVcJx5IUXkqVeqt1CQzak,1624
326
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/parallel.py,sha256=Q54wFSSRBp-kG2MhW4eOoXE1W9g-SDVhN8JuphDERsE,2029
327
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_metric.py,sha256=nftLaTOKEmqvSWr-c20f9hyyvNnd-Hg3E46KwqmkjLc,6149
328
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/utils.py,sha256=hhF2MuPo5n6uM0OCgTHCNIgscNVhXRb3koqU73AErwY,15924
329
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/vqa_metric.py,sha256=XkAiXk1uE7lsWQQXvjnHXZMsga8B9FVyq5qG8ghePK4,8980
330
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
331
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/readme.txt,sha256=QO0K9z1ethy_lgs9vaxGN1u5DnPFsssp8z62Cni24iw,1424
332
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/rrc_evaluation_funcs_1_1.py,sha256=qCuqDtsCfxAiQHYLNdHU7BQ9kLIZ9iyfmRxtIrGOBck,20349
333
+ evalscope/benchmarks/ocr_bench/ocr_bench_v2/spotting_eval/script.py,sha256=7HzM1PEw8wNOhmQOsZe582Y2rr4u66Q3JKVvvMasntE,19565
334
+ evalscope/benchmarks/olympiad_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
335
+ evalscope/benchmarks/olympiad_bench/olympiad_bench_adapter.py,sha256=zePVmGjmyuwCWVb4h1PIQKAIFqBehwRwO2WOD0KX_ik,6565
336
+ evalscope/benchmarks/olympiad_bench/utils.py,sha256=w7vEZcT3vCVq8_DSMgAjZPpVFVHStJPJYsPkrs-yOFM,21412
337
+ evalscope/benchmarks/omni_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
338
+ evalscope/benchmarks/omni_bench/omni_bench_adapter.py,sha256=IJkRSokQC6MF_pN46Yofr_NaZaNt1XZFX1PUBmX4-qA,3651
339
+ evalscope/benchmarks/omnidoc_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
340
+ evalscope/benchmarks/omnidoc_bench/end2end_eval.py,sha256=71IEdeDsldtoFmMb1c_Pyugv-Wx-WOVIvccRkPvsJdU,15916
341
+ evalscope/benchmarks/omnidoc_bench/metrics.py,sha256=DZfaL5BlDjnW60kRnnfmsMgldPOKX0MJ2tAdsBf4dI0,20620
342
+ evalscope/benchmarks/omnidoc_bench/omnidoc_bench_adapter.py,sha256=YpXl-HUiD-VjtwtWHG4KSUw6GAYIeKnpgqEXsweWnKY,6164
343
+ evalscope/benchmarks/omnidoc_bench/utils.py,sha256=Db6QeIq_bc6Dl5xdYel5G7tnWib9_vn_KFiKeFN37IA,74435
344
+ evalscope/benchmarks/piqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
345
+ evalscope/benchmarks/piqa/piqa_adapter.py,sha256=V3-8a7Ah04UgEWzYrQfGKiPk4xvpLS74G4mJWM1MqPI,1075
346
+ evalscope/benchmarks/poly_math/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
347
+ evalscope/benchmarks/poly_math/poly_math_adapter.py,sha256=yO8CSFXIoe8AzKIXq7IffefTiWPQrdh-4igt09KPb8o,5545
348
+ evalscope/benchmarks/poly_math/utils/instruction.py,sha256=v3E8TnoWlooL_Ms5CQySzMmdyPKHAO005tGtTWMviPo,6901
349
+ evalscope/benchmarks/pope/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
350
+ evalscope/benchmarks/pope/pope_adapter.py,sha256=iQFcAjh48Su76e8CV-Tj2oVzzls0mUIYRUUyknj0dqs,5035
227
351
  evalscope/benchmarks/process_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
228
- evalscope/benchmarks/process_bench/process_bench_adapter.py,sha256=XN3F6NH7mF4ibwGX5nI01sqEHz05UQFnBAyfAe14QYE,6174
352
+ evalscope/benchmarks/process_bench/process_bench_adapter.py,sha256=7Bri8ZALJAMKKf1_rtQw1bH9-IuvutwZ9gMNXBgQpmY,6200
353
+ evalscope/benchmarks/pumed_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
354
+ evalscope/benchmarks/pumed_qa/pubmed_qa_adapter.py,sha256=R1AjPTqqV8N7IvBNx3Qydd39EP5QcA4BffG3a1WEDP4,6778
355
+ evalscope/benchmarks/qasc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
356
+ evalscope/benchmarks/qasc/qasc_adapter.py,sha256=rhYedQBhrCkv12b4-LWRSfY6LGNgV0I5n2Lm2BEFlak,1128
229
357
  evalscope/benchmarks/race/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
230
358
  evalscope/benchmarks/race/race_adapter.py,sha256=KibT9gHpIOZhTcWihG0dUDAX4gAHa2g1WdGPOcEP9OY,1705
359
+ evalscope/benchmarks/real_world_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
360
+ evalscope/benchmarks/real_world_qa/real_world_qa_adapter.py,sha256=J2u0J9d31uvkoz9nBI9tCMqG27hmYwdLQPPef9jx_pg,2788
361
+ evalscope/benchmarks/sciq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
362
+ evalscope/benchmarks/sciq/sciq_adapter.py,sha256=m0TMtTVR-cRQ0oMncgbN7w-v5d_m71hiGeIE5WRa2mA,1249
363
+ evalscope/benchmarks/seed_bench_2_plus/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
364
+ evalscope/benchmarks/seed_bench_2_plus/seed_bench_2_plus_adapter.py,sha256=ngUOFhP8YFOE8ximkMg5U6TGLZMIXPHJsVJUurvbzM8,3064
231
365
  evalscope/benchmarks/simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
232
- evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=_duveAliSaPUqVSLQ2TtSv5sfwvFFy7t-MgIIokQ24s,9017
366
+ evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=OIVGeFVLEpZp7z2a6JLf_qdRjNhu1-GJgTVL7ocZFiU,9013
367
+ evalscope/benchmarks/simple_vqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
368
+ evalscope/benchmarks/simple_vqa/simple_vqa_adapter.py,sha256=3ioSompYERllFE6yc3yZLl0NKWypRjg5d0uVf3b-4d0,9530
369
+ evalscope/benchmarks/siqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
370
+ evalscope/benchmarks/siqa/siqa_adapter.py,sha256=qpPbEaGrVMc5U0x8hwWRz8gR-1HL0Uvaa5QFInAsLm8,1342
233
371
  evalscope/benchmarks/super_gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
234
372
  evalscope/benchmarks/super_gpqa/prompt.py,sha256=wQ8Y4NAvQJRhPS7gsrUBBzeM_UCHsHOloB_t5WfnIO8,4707
235
373
  evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py,sha256=SPqpBebiHj_oyEqU94p9NSqhVkO0KeXQYcBmpfH81nM,6888
236
374
  evalscope/benchmarks/super_gpqa/utils.py,sha256=OK_oT-DnWNssITEwu_Zc3Ty5v21n0IaJQYftK2cpwmQ,3401
237
375
  evalscope/benchmarks/tau_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
238
- evalscope/benchmarks/tau_bench/generation.py,sha256=SankPe87Zi85CGlSKWZyOYo6Q4gRN22I7fkl3ef547U,5165
239
- evalscope/benchmarks/tau_bench/tau_bench_adapter.py,sha256=2Gjvc8RVavcIHQPDXI5d6zxpeHqghRnOhlzwWjGKc24,6438
376
+ evalscope/benchmarks/tau_bench/tau2_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
377
+ evalscope/benchmarks/tau_bench/tau2_bench/generation.py,sha256=aMa_I12HmRUj33ELcKgvYCPE-sCimlpdGyean5QMSaE,5387
378
+ evalscope/benchmarks/tau_bench/tau2_bench/tau2_bench_adapter.py,sha256=49M4ABPjSbR5Pkus4RFcnnprN9b3UbSjwXqlJ7PbwHI,5748
379
+ evalscope/benchmarks/tau_bench/tau_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
380
+ evalscope/benchmarks/tau_bench/tau_bench/generation.py,sha256=d7J5xrxEI-0BYxdSuxdDavcR7f1ipBdpQsKZzwyzGds,5190
381
+ evalscope/benchmarks/tau_bench/tau_bench/tau_bench_adapter.py,sha256=vQJdHvvtWI7Eh5zp3M9vFSYmJ-GM4386PVLdf4IONYI,6443
382
+ evalscope/benchmarks/text2image/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
383
+ evalscope/benchmarks/text2image/evalmuse_adapter.py,sha256=g-Wc1qTg-xWLTjiZPo8zmQud75ac-8mBpYRxOHfiO0g,3024
384
+ evalscope/benchmarks/text2image/genai_bench_adapter.py,sha256=1GDB3gS9zwrfb9C83LQdQyN7bvvqeYuu5ulJ9Igmi2k,1876
385
+ evalscope/benchmarks/text2image/general_t2i_adapter.py,sha256=CHy9ufvrVHc_5WkGVR_F-5wfLQVFtxwubZOfdpx9rd8,1354
386
+ evalscope/benchmarks/text2image/hpdv2_adapter.py,sha256=8-vWCV21eo_e9EbxDB5mGw2cFzD4OUQPLB66FvlO9W4,1781
387
+ evalscope/benchmarks/text2image/tifa_adapter.py,sha256=4CcprucAe25UpTZRV3Qgb-8jbeNHtXNRWHw8RiYvfJA,784
240
388
  evalscope/benchmarks/tool_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
241
- evalscope/benchmarks/tool_bench/tool_bench_adapter.py,sha256=BHsesDDELEINdbWSR3WKCQGZ6MqWc2LiOZA3MbTp2_s,3805
389
+ evalscope/benchmarks/tool_bench/tool_bench_adapter.py,sha256=Lt1iSe9C0PgayqfgmjF0kGllFqizROqp4efjSl9SUUY,3790
242
390
  evalscope/benchmarks/tool_bench/utils.py,sha256=led0d-Pa3rvmWkSWhEnZWP00fceudgESq5HXAQzJGls,7042
243
391
  evalscope/benchmarks/trivia_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
244
392
  evalscope/benchmarks/trivia_qa/samples.jsonl,sha256=1isBD62PGhCiNbzQa-GFrHHL4XLHIkojWfgSvn7ktf8,3445
245
393
  evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=oZAiCmBpZbBAgzAKPfddaJWMckIyaoRM7fB2XJ5EoQU,2614
246
394
  evalscope/benchmarks/truthful_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
247
- evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=LkmJFWzLpk0ryUf_XVZvEBIVTcSJ2a4pB9bh7k0DIJI,3519
395
+ evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=W7ESUAcLsHwbssiiSCQNUeQcqx6JEeW7FSQiBFycS24,3512
396
+ evalscope/benchmarks/visu_logic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
397
+ evalscope/benchmarks/visu_logic/visu_logic_adapter.py,sha256=8dK8_HFxDhWTvCC8WTZjadChP6lNzgsFp_5qFSRGFoM,3277
248
398
  evalscope/benchmarks/winogrande/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
249
399
  evalscope/benchmarks/winogrande/winogrande_adapter.py,sha256=LWm6qZd3pJbtpcERq7WPK3adwY3uVm4wiUgfyEI_uHE,1310
400
+ evalscope/benchmarks/wmt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
401
+ evalscope/benchmarks/wmt/wmt24_adapter.py,sha256=58BhTjdfJRQS2WtGxwdmgFC5VTx2XjKU0pi7KNh0iO8,8759
402
+ evalscope/benchmarks/zerobench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
403
+ evalscope/benchmarks/zerobench/zerobench_adapter.py,sha256=pqnJEx4uOi3bxwYKqLxrxU5DX9p3F01N2itzbG_-VaU,2739
250
404
  evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
251
405
  evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
252
406
  evalscope/cli/cli.py,sha256=qXQ6k9GBkRy2dmBxM24tbVP42bQDyM6G7kkc32LdpCA,860
253
- evalscope/cli/start_app.py,sha256=dV63nvBYEUl2sGeVxoUH4IJBXJSLecaq293i3alBWxo,794
407
+ evalscope/cli/start_app.py,sha256=LqJ3cSBY8FsM_JjInw4jlpitjaVoIZscUShMpDRPbro,1030
254
408
  evalscope/cli/start_eval.py,sha256=MXhVDeaMFd6ny88-gnVtQflH660UaDj240YGYnHccx8,775
255
- evalscope/cli/start_perf.py,sha256=5hLi5jWgM9BJPXLd8d9D1zqrcj_5c0KvkfB1DgD4_RU,831
409
+ evalscope/cli/start_perf.py,sha256=V8DwVPXTGmyDPma7Yk_pJbLb4iVkDj6Y3qPGHV03sE0,1082
256
410
  evalscope/cli/start_server.py,sha256=01iDaEwLx59xRUrrZ_nhQE-QjUE1Rk5d43uMQ_4owbI,3677
257
411
  evalscope/collections/__init__.py,sha256=x05hFLrjGsdtuHtc6PyQXHNuucVdYaBN9ZrM8gBiJWg,720
258
412
  evalscope/collections/sampler.py,sha256=086pzXQO4CO_QYCd10z149Sjh6sBpRBeIHf5OTLOVu8,4896
259
413
  evalscope/collections/schema.py,sha256=yzAlnH0O7iiWB4UnkFXI_Dvxcsq9hDgl0aGK2OpyBY8,4158
260
414
  evalscope/evaluator/__init__.py,sha256=KzYmVTfU-1pdX7va7l3B1-5QKWG07hj1B7rYkMmxitY,91
261
- evalscope/evaluator/evaluator.py,sha256=IY0LElXZXfe2HW1v99dKkN3qhyzo0WO4aR8OyxUny3A,13545
415
+ evalscope/evaluator/evaluator.py,sha256=B4E6vTnG2v7efIsTwBHSyONT8GOwPwmyC6m3siubK08,15964
262
416
  evalscope/filters/__init__.py,sha256=AsXwKYDjGhFsJvtj036PRjMOPsHGt-CRicnHTtM_qA4,51
263
417
  evalscope/filters/extraction.py,sha256=KLFr_3XYsrv0PTvmXy0ugj2sqv2ZOWJFV7G_MmGjTHk,4146
264
418
  evalscope/filters/selection.py,sha256=yiJu2JjXDH_lgfEtB9umkGcA3zpo3zvnyoq2mKrXbnw,1609
265
419
  evalscope/metrics/__init__.py,sha256=1giVHESSjn98uBiAvYm5uLsmRQwmf9NHPSt7OT_QJss,1615
266
- evalscope/metrics/llm_judge.py,sha256=xNmchB6ZDlrQnxv-Vit_zcQjeAH-C0o3m4bF4OFDRCI,8174
267
- evalscope/metrics/math_parser.py,sha256=BMfautQtNNiF9f2DIEfO6SXSn_GYhzaddAjGWG10MJA,17257
268
- evalscope/metrics/metric.py,sha256=6la8Nq2E_brArDcNwkbRX3ECef0AAE3IrBCfUVE7UKc,10176
269
- evalscope/metrics/metrics.py,sha256=VxAggzEfaLKxWcXyuve8QbEBwV2W71udVyt0gynzGec,14134
420
+ evalscope/metrics/llm_judge.py,sha256=XukhH9PQtIZAcbjJlOmOD9ye3ngRv_IGKKJE9jhheOE,8653
421
+ evalscope/metrics/math_parser.py,sha256=gJ1NR2Mcyzt9qMdR8I0-6U31Jzoe8a6yUuwvayYPi4c,17979
422
+ evalscope/metrics/metric.py,sha256=0NKTUgNdvL1T4171Y6-ImsopsnUqx2AioSZTBKB4SmE,21975
423
+ evalscope/metrics/metrics.py,sha256=g4EPKTLe_qwofg1UAD7vZhpqVktsSjxV-y1BoaD4WiM,15324
270
424
  evalscope/metrics/rouge_metric.py,sha256=bqvSotuDdC0MEKmt8v6y6tBTBx0S3Ma-tfF-cMCckA4,4645
425
+ evalscope/metrics/bert_score/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
426
+ evalscope/metrics/bert_score/scorer.py,sha256=VobwRtTYS9ENHn5284sWkUlw5LBBNXvViZh185PkiPI,11969
427
+ evalscope/metrics/bert_score/utils.py,sha256=k7ekv1PBNkGMIj3W-KfkIV-i_ryMErcqBtAWjXv9gos,29659
271
428
  evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
272
429
  evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=T91PgJfi1As7BR7I-Hq6rLlvHAtMB9JpBw9gMTH8VlE,12114
273
430
  evalscope/metrics/t2v_metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -344,9 +501,9 @@ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py,sh
344
501
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/base_model.py,sha256=OOr1JD9kTlUGXZNG5b3kvkUaNz7QTmhaGoHhIKL69qo,7613
345
502
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py,sha256=Ns7oM4KpKxWZTo8Lefe4EDFw-jzp5633zAArcWjoVZA,9772
346
503
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py,sha256=KIF5tsiE7a5dbDfa-IKwzuzMUpuEAQPrm1nWFFtAeoI,20032
347
- evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py,sha256=uhaehowhTqRhQtq_dVCgF-9Iu4yU19AMxx2sJimYwlA,52711
504
+ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py,sha256=85ZvV2gKSnsbP5941PeJ-JJ4t8_lOYQe1EOxrHlIbNI,52728
348
505
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py,sha256=o5ykt3Q_WQlNmyxjQaS2-KPLGq1xqLZixNYam_Bs6NA,18701
349
- evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py,sha256=aBKdQQS7cHMPgYqIknCdHCZ7j2_QLACPn_jU_njiMIs,46840
506
+ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py,sha256=NPDpIRxjiroafZk5Z2uA9bC8Bi-yXY7um5HXxThF7N0,46857
350
507
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
351
508
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py,sha256=s7EkhtrIJ0LPUuLBArws8N23R1MoIoNaYUjwsbUqRkY,7994
352
509
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py,sha256=FnUyxxazEVaP69pAq9cig3j-mcX37BX-unPj0SVKUJI,3805
@@ -366,54 +523,55 @@ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/bl
366
523
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py,sha256=TOAI-KaUrtKjR1GNU_WwNXNpb9gGT-KX2FYe3muv_e0,4275
367
524
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py,sha256=-DprR09KYuwNEzEbhPvFRI3MR4_VdPMUGLPN6sL9Ym8,14625
368
525
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py,sha256=S68U0DxWYGDmreRbH5yLDHBNN9PsczY9H0Uik0hO-ds,13872
369
- evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py,sha256=i1XlJe_PTSmiPkZKIhUXC_lc0-z2ewNYo4W1DvZQxjY,36678
526
+ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py,sha256=zv_WyHi67hvgHQ4DkZ8a4UoPcgrADKayqVtiIq-p3V4,36695
370
527
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py,sha256=p67DDiFS-676z0z8jPj6NwXwNjEsqTXaXCh3g2UiDno,840
371
528
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py,sha256=LqMHlUTy2LEzoVwjALtrAw0UYmzIuHnFjQiVmn5nv-I,605
372
529
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py,sha256=d4HInkL_Phk0Bgg2cWaOvhsPa6lkqDeovFW86PL0I18,6371
373
530
  evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py,sha256=Epk72q5iTdzRbuzOR669QqAUMgrFFngAU8Z3Qy9KLbM,11209
374
531
  evalscope/models/__init__.py,sha256=RmW2S31BHBhMN49_VVF_5PJAk-TsuZQkuF2ALShbhAw,556
532
+ evalscope/models/image_edit_model.py,sha256=oVjGgebnFu3ZXBJLNn62rJ65fcJR7DlG4qEVxisPJ2Y,4104
375
533
  evalscope/models/mockllm.py,sha256=t1fFAHkEb1n_atOCfnGteCX3DWp774lnWcHzi5lBjwM,2511
376
- evalscope/models/model_apis.py,sha256=-yj2cY0Z0Ku6ZTnFqpoxArHLJyoUdq4YA_ChLo3_xw4,1176
534
+ evalscope/models/model_apis.py,sha256=ZkZ_nfbeAFJnCndRvRIRLcbmJFTMhGRBi-WfMu0uZKE,1922
377
535
  evalscope/models/modelscope.py,sha256=jSFkho_Ir2py54y_Bwj9jpCoY2mMKkZ8ORzne-ldAIE,15806
378
- evalscope/models/openai_compatible.py,sha256=8WlWtu7EWr3Y5e5ErpeLQ7ZKfN4HXkFN3gV_jl5p1NM,4528
379
- evalscope/models/text2image_model.py,sha256=-NMLtZuT7L86HpkMpsz_gNaA5Z9_6p1MYzmjYZN6mvo,3929
380
- evalscope/models/utils/openai.py,sha256=u343L0OVqv4NbVSICSzwfWXh3QEyIIIv9ZWrBzW6IGk,28013
536
+ evalscope/models/openai_compatible.py,sha256=7UxS4TZBYw7jGzuu-dUs6-5g1_nydtW-0mHSxkl74w0,5438
537
+ evalscope/models/text2image_model.py,sha256=Sdiyw6vewjVTiXK8RFEh1pohOhDge80EoIWYpnLjr5Y,3929
538
+ evalscope/models/utils/openai.py,sha256=A93Wd7egqmu6DNLeibnRAPLQJXTB5ucya6aBQSHkHGk,28475
381
539
  evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
382
- evalscope/perf/arguments.py,sha256=lG2IOOzxg29pdnF6IobzPcqEcYqopulFpVU2QzRaEJA,11429
383
- evalscope/perf/benchmark.py,sha256=w6gb5ofGAXxBdp6hejowKgXu0rv1xfTqhg5VYBTcGc0,7885
384
- evalscope/perf/http_client.py,sha256=4Ov1Cwi7gMgO05ZmazwyfYjUGAQNGWn7nbfl1ljRNh4,4610
385
- evalscope/perf/main.py,sha256=WZbBgFhIj9KqxzC7_NZxDlou019_EXatsHRt5vqDhFg,3439
540
+ evalscope/perf/arguments.py,sha256=JHB-JIEHq5p3zoHeKn6dkelGq0JrMVMRne-wbXK2yhg,12892
541
+ evalscope/perf/benchmark.py,sha256=Uc6BJJGYTsAnfFljPy0WJIXcapHOIwvym3o0yPRTVqU,6964
542
+ evalscope/perf/http_client.py,sha256=8xJFYja8FoQA0MDTj2NcxPkAmji4n81fsaw1gRuL1sA,5152
543
+ evalscope/perf/main.py,sha256=eEL0qUdNPMyHr3ZTixTfZxKN4IIw3gz3sw8sq3S_vs4,4015
386
544
  evalscope/perf/plugin/__init__.py,sha256=Ztj4h1_JYJqbbWkeuDTj5aTRyGQf5Woc4xEIyjcokVU,94
387
545
  evalscope/perf/plugin/registry.py,sha256=GhLe-h1rGzya2bgIUaV5VymQIaHqI7h5SG_i4PoGAm8,1967
388
546
  evalscope/perf/plugin/api/__init__.py,sha256=7RsGdYTSfnW6iVpveEzNu8v4x8Yc8H-Kk39DqOHMrd4,152
389
- evalscope/perf/plugin/api/base.py,sha256=9cX4xwTzy5ycnWqmQqRGMLasTEX6jVlobtADkh1KwXE,2782
390
- evalscope/perf/plugin/api/custom_api.py,sha256=VYJO2lUt9EKdWz6zeYCfvdI0MqfcsIgcKvxqvY5C-3k,10376
547
+ evalscope/perf/plugin/api/base.py,sha256=LLBDKOWUXYbLLLTtO86X1Y4Erbp5egs2WCXGj4my754,2822
548
+ evalscope/perf/plugin/api/custom_api.py,sha256=HHvhNlqNQr43GhIC61yoa54QCEAy4MRMmJ0kBy-rnsQ,8305
391
549
  evalscope/perf/plugin/api/dashscope_api.py,sha256=Miv2pzMa6sxZyYYJhCzcbOI_QHuZx7tazKpb6Not7ck,3627
392
- evalscope/perf/plugin/api/default_api.py,sha256=kjuHQ-zRHe5WU4ofSzWBpWbIxBQBOh_ucu1z2g62gWg,4315
393
- evalscope/perf/plugin/api/openai_api.py,sha256=oewwOPhv0BLdC7n3BUngpVrDYst5wMrBEPhN8oGMKNU,7703
550
+ evalscope/perf/plugin/api/default_api.py,sha256=A3_dUduoBo9-xUdYsKMI1X0WUw_wHsJFNe5hTr9LUEo,9418
551
+ evalscope/perf/plugin/api/openai_api.py,sha256=UVo9tAnqZbVNEQwAT0wOZb1Abbf-yQmr3iDKHwXDoI8,10628
394
552
  evalscope/perf/plugin/datasets/__init__.py,sha256=qzeQ9BrJhiJJm1wHaFeOQkvXXdSd15Ucspbn5zjs-6Q,495
395
- evalscope/perf/plugin/datasets/base.py,sha256=-3Ihnp2hYvZyPnP8Gh2Pu8ovlLNFHyZnNgRu3WHG4d0,2714
396
- evalscope/perf/plugin/datasets/custom.py,sha256=yoRHTvTGAglaZ-mmRkPjYNMG7uZYuT1_KrBxnl2i0qg,1385
397
- evalscope/perf/plugin/datasets/flickr8k.py,sha256=M-w1UjOMkA6Uh9v-SURDrm1YCL-m1Cn1u1cIcEJFDpY,1044
398
- evalscope/perf/plugin/datasets/kontext_bench.py,sha256=-KsoXS7nAd6hzN4oCe85zcLkZQT-1IGWQFThuuvE7vo,1092
399
- evalscope/perf/plugin/datasets/line_by_line.py,sha256=F4ppdjKKLzFNf_16h6S-6nAU4lOfOFI2-tPgIeZDTMA,996
400
- evalscope/perf/plugin/datasets/longalpaca.py,sha256=JjPGYP8NdPmP48wff2fL5IZQfajXL5qhZBvKmZxtfW4,1336
401
- evalscope/perf/plugin/datasets/openqa.py,sha256=5PqqiIvNTLlRrPb8PWqMGQyWRb6LuIqipYn67-xd-dY,1519
402
- evalscope/perf/plugin/datasets/random_dataset.py,sha256=NNAXvgFPkLDOSpYNex1DyE4X-ELtQRm13_oBooO30j8,3514
403
- evalscope/perf/plugin/datasets/random_vl_dataset.py,sha256=F3yA9Ih3YO895lZKCo3i85LeKTzjvGcvhzc8UNN-gUI,3240
553
+ evalscope/perf/plugin/datasets/base.py,sha256=PFBMdo3H_Hx2jOXNrMb97DvJ5gJg6QajSYymCgTXKmo,3629
554
+ evalscope/perf/plugin/datasets/custom.py,sha256=kCofjHfcihPcsc1XwyLxn9QG9E88eZ5qAQW7nW6ID0c,1311
555
+ evalscope/perf/plugin/datasets/flickr8k.py,sha256=nhHiGNhXX-2c17NQ5q5Q7FgV2hB8XVeeAP8dKkboyHE,1033
556
+ evalscope/perf/plugin/datasets/kontext_bench.py,sha256=cN70hiBX1940IWvNWZG9YGE4vO1yj41Bo7bqmOWusoQ,1081
557
+ evalscope/perf/plugin/datasets/line_by_line.py,sha256=L3lj9evcr3q-Mcemyuy2WauBB5c6O-ttnIVw1t4UJUE,922
558
+ evalscope/perf/plugin/datasets/longalpaca.py,sha256=abFLvrRZFsno9IUr_bpvhMWHL9X2sahlIpGLUb-5BxA,1262
559
+ evalscope/perf/plugin/datasets/openqa.py,sha256=UlbHhzGoQTBXa4foEFhRTZX6v7So6pR-ExFhU2ws8YM,1427
560
+ evalscope/perf/plugin/datasets/random_dataset.py,sha256=GPuC5ovi3BW84RCiGSDd2cBZ3jRmFrtMRsxEocc1ud8,3347
561
+ evalscope/perf/plugin/datasets/random_vl_dataset.py,sha256=e6exWQnupWkTDNwt2MmEK-hccuxEDmWLJRMM70onKi0,3230
404
562
  evalscope/perf/plugin/datasets/speed_benchmark.py,sha256=J6q7AF_Re5eHLVejXEw9c1jlk1T1PPmist0yO9UFTPE,2432
405
563
  evalscope/perf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
406
564
  evalscope/perf/utils/analysis_result.py,sha256=aoT7JD2zAzBeuZUfncKhJ2odX_7KnymwOmNB1Upam2c,935
407
- evalscope/perf/utils/benchmark_util.py,sha256=91hZabkrDnv-0hgmqHi5TmyCT1ztbGbhu3Y5pB6vgRU,7157
408
- evalscope/perf/utils/db_util.py,sha256=HAISq6M7xCD2gjUEqqfbK3FjBxA-tvr_n-751tU9ypo,11634
565
+ evalscope/perf/utils/benchmark_util.py,sha256=Uf4vUAsfgAZs2qsyv9cRY_i87QNEHl17XMhGgXq7wFw,8048
566
+ evalscope/perf/utils/db_util.py,sha256=lr26ah_KRznBBu_ssxXki_PgtELk5bUJV2JaM4LaeNI,11534
409
567
  evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
410
- evalscope/perf/utils/local_server.py,sha256=Bp4pWmjZS6CDlumedea_XRsAqWuoCbmr3z4TPOk2vEc,4768
411
- evalscope/perf/utils/log_utils.py,sha256=NWSK_ITG4yoVx5GMLbIRGDoXSs90s7X3mftdm37Os2U,1666
568
+ evalscope/perf/utils/local_server.py,sha256=dMoX8p6aCQq1JnoXxcyWknadLdBwpfQhvKwk5fn6G4Q,3727
569
+ evalscope/perf/utils/log_utils.py,sha256=YY8mnpJoHMlP6jtmEq7QujyuxhSUF1vqLk8TpBAkbY0,2162
412
570
  evalscope/perf/utils/rich_display.py,sha256=AQmXv1EuA1-IGgco-Jy1NLOmTKv4eBFH2K4QS8OoGVo,8206
413
- evalscope/report/__init__.py,sha256=qpiOJkM4PO8l9X9ZPUsqBFBfNOzYVEkYfwisfli9bJE,907
414
- evalscope/report/combinator.py,sha256=MAiOCj_q5mXm8-3lARvCSG12jUVEdJ8VcoEHJapoWzo,4134
415
- evalscope/report/generator.py,sha256=_ovCzV7E5SfFWLeKIW6CotSqiqiJ8qkNQU5UlPGscSM,8041
416
- evalscope/report/report.py,sha256=KxboijAVNENxYHjiwyyqW_aQZ0F2CyJ6MbqUJTRHJMs,8273
571
+ evalscope/report/__init__.py,sha256=rjjg_4PHuUA_15XXjOgPjO6cOm08LOi5yUGYzOK6KX8,1216
572
+ evalscope/report/combinator.py,sha256=rpZJsMiVF9Uf4niP5WmZVaLcITPEXdER9Etgqn-BsU8,6740
573
+ evalscope/report/generator.py,sha256=t2R3WGa4SowTRUPOgITtyTR4QDiJ6i3FH__byDKZU8Y,4959
574
+ evalscope/report/report.py,sha256=lEBD_E_RJiydFTaGFNLIMTFxNrqv8QcLZb_iuUg5HB0,8479
417
575
  evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
418
576
  evalscope/third_party/longbench_write/README.md,sha256=1yLKeSVIcihpoc4KXr8NpK86JbcLssCPx76aOKdPbYI,5431
419
577
  evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u7z6OI79czoBlP8lX4PVo,126
@@ -448,45 +606,23 @@ evalscope/third_party/toolbench_static/infer.py,sha256=rsADLhEd2IBcC6EI9aD7hSJmo
448
606
  evalscope/third_party/toolbench_static/requirements.txt,sha256=OW91Z8hfzh7yQUYgP1Di_E6DgNgGoGP1UcvnqrdCR68,22
449
607
  evalscope/third_party/toolbench_static/toolbench_static.py,sha256=xE__eXvSwHmmSh1tXNvyBo6MCO4mDlYTbIYl9OGEfNI,2120
450
608
  evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
451
- evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=GITEbyiER10Zi-ZWpSqYCdAsiVtNeGK24hvR3kmYn2s,2689
609
+ evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=hy0JpjSEkCJh3z5ZnY8gGfdJ2ajkS5zRl-2ZQq6Gu8A,2527
452
610
  evalscope/utils/__init__.py,sha256=5OH8cOoX3YKMKUu0dMRvwzckXligIbUV-1jjJNXlpGI,2231
453
- evalscope/utils/argument_utils.py,sha256=D7qOH85wf7LKh_cJ2X51OEaL7CMaddydmHZkfoYpvLk,1952
454
- evalscope/utils/chat_service.py,sha256=47VmV4NdiYazfSAPww5wPf53L5avw6VETYgyGZyGvGc,8758
611
+ evalscope/utils/argument_utils.py,sha256=zYsqWLFlVeiLSQdFruBI_seTUEVTJ87r8MKwL2JNGb0,1951
612
+ evalscope/utils/chat_service.py,sha256=sSki2pKGQP3UjcIf_lbO06afI-vsaUAqglwX__wUDEw,8766
455
613
  evalscope/utils/deprecation_utils.py,sha256=aDv3HFNcJFZ7rxNgALQP0-ITO8L23HC_RX-C_m2i34Y,1610
456
- evalscope/utils/function_utils.py,sha256=a752Z4Xb1rznnLJU9g5Pxqd3r_XzfLzAkdcjSX0kOVc,650
457
- evalscope/utils/import_utils.py,sha256=BSdp7RQSZu67129TBbtJvMWU0CfCFu864K31eiM3pr8,2975
458
- evalscope/utils/io_utils.py,sha256=elAFpyb5FGwV3AZxapkXqZmjtJCSvZZVe0QQEH4nxWM,10020
459
- evalscope/utils/json_schema.py,sha256=MLCS8cSLXF83UPebBaVWDfXJnf0qXsXnr-bIRG88cI4,7485
460
- evalscope/utils/logger.py,sha256=SPhhXo9gyZtWDYDLumII2CEmwHsaW8Bu1IjK5UqWrKQ,5273
461
- evalscope/utils/model_utils.py,sha256=q0mmcfUJVks21NHP8awTQk_1q6ruupjzIBN_Xo3wt40,2394
462
- evalscope/utils/multi_choices.py,sha256=ZEpN8LcZfXhhuATeMZx_uEnMg3l981J_OdSL90iFoZQ,8951
614
+ evalscope/utils/function_utils.py,sha256=Zu3njXZl6U5AhTyPUfhGXrdCRUCgY1Kvy6gtBpOrvHA,10380
615
+ evalscope/utils/import_utils.py,sha256=S0WQ3gt4zpwJHjGcyC-604pWWExg3JV7f3wzoOH-tuo,5794
616
+ evalscope/utils/io_utils.py,sha256=LSPYaIEYv8oj4ozAcbxtSCbsl4edWrr2aI5CP161DvM,14133
617
+ evalscope/utils/json_schema.py,sha256=GVP1m6g4mBrsFmOWOOVnmvl2joOz8gTlGEytLv5qy7s,8451
618
+ evalscope/utils/logger.py,sha256=su2D4d3apydmjiYrEBX0p2m8A6tPOlAupmnSfo4jttI,6807
619
+ evalscope/utils/model_utils.py,sha256=mdtYoHhUdfpxUtnS52XZjNdO3uSK4yeIBHT3aDU7s-A,2455
620
+ evalscope/utils/multi_choices.py,sha256=0UJbgr5eXNgitPC79JLcyUU-OXg9BlM-mVk-fWtUSno,9881
621
+ evalscope/utils/ner.py,sha256=gxvUURZVLJqZUrIqCy892rAAJ2ydYiGG5ZKPW_mpHsM,14148
463
622
  evalscope/utils/url_utils.py,sha256=9HcFt9uZNbOJR3ADUFQ_dBFKziHV6H66Df7HYs1M4Po,1757
464
- tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
465
- tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
466
- tests/utils.py,sha256=Fgm0CU6ilZjCGOfOMJH-Trxy0UIAGbhvy0Ijy_zDGUk,323
467
- tests/aigc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
468
- tests/aigc/test_t2i.py,sha256=fciaGsOrkOpT4WQlsnmjrqw6qolCzI0DGyWQAJkM-Es,4513
469
- tests/benchmark/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
470
- tests/benchmark/test_eval.py,sha256=fHAr4h2YjqIVk-FHp93HUZvRZ1fvlVFd1EUeRwrIwYw,12559
471
- tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
472
- tests/cli/test_all.py,sha256=a3G0LMgQx3M97uy0GfX1DFxbA7zWofkxgtwT8PMorQI,6268
473
- tests/cli/test_collection.py,sha256=OUm2_Qt0zkQehPTAmUaGRNBes8ewr7wYfE0E-gUe1J8,4386
474
- tests/cli/test_custom.py,sha256=9z_N7Re712xI62TqVSTBdzB_iFFEUb55wcWIcGvJb84,9254
475
- tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
476
- tests/perf/test_perf.py,sha256=AEWvpN3ID6s-9MEoaZjQqUM8VVsqgk_v9KX8pDgvozA,5864
477
- tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
478
- tests/rag/test_clip_benchmark.py,sha256=YmfezEzqBrl9-Ga2pG4YXs0ARcD5gWmuzINjY08tPpM,2695
479
- tests/rag/test_mteb.py,sha256=fdNQIyUEzE7puPCKw5QhCHTEu7hz-ieHeq1xCWGh6IM,7246
480
- tests/rag/test_ragas.py,sha256=5qozXvPFIb67T-igJv87ijlOgkPnqgkkBVXu6Ht4D0A,4554
481
- tests/swift/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
482
- tests/swift/test_run_swift_eval.py,sha256=YbIhYNoI4kAB-ox-OXAKUifLIXTFqP-xGZicrAgK_V0,5784
483
- tests/swift/test_run_swift_vlm_eval.py,sha256=RwrKkc1WHEZxetM11cGL81G4faKCn7SYn4VlwL03atI,4934
484
- tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=UAUtOCQ72xbm8s-sov3cBEpYVDy189wpB-qOL3KoU7M,6053
485
- tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
486
- tests/vlm/test_vlmeval.py,sha256=EDQRkYfSyOICUwo_tm3p-puaE_xdFmqOPkrt5etxsqM,3307
487
- evalscope-1.0.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
488
- evalscope-1.0.0.dist-info/METADATA,sha256=FKr7sZCbyX_HxicgCX5rHrZz19STzLSK1Tgmm0CrWlg,39723
489
- evalscope-1.0.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
490
- evalscope-1.0.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
491
- evalscope-1.0.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
492
- evalscope-1.0.0.dist-info/RECORD,,
623
+ evalscope-1.2.0.dist-info/licenses/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
624
+ evalscope-1.2.0.dist-info/METADATA,sha256=uERC07rUVf9mGqWR3b4-t4XyJW1OUmW8waA5CHFclHo,35423
625
+ evalscope-1.2.0.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
626
+ evalscope-1.2.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
627
+ evalscope-1.2.0.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
628
+ evalscope-1.2.0.dist-info/RECORD,,