task_id,family,primary_tag,split,score,success,steps,elapsed_s,error osworld_0a0faba3,docx,check_tabstops,eval,0.001,False,4,18.35, osworld_0b17a146,docx,compare_docx_files,eval,0.001,False,4,14.57, osworld_66399b0d,docx,compare_docx_tables,eval,0.001,False,3,9.2, osworld_0810415c,docx,compare_line_spacing,eval,0.001,False,5,15.77, pptarena_case_60_fix_text_placement,pptx,"Alignment, Distribution & Z-order",eval,0.001,False,3,10.85, pptarena_case_7_update_quarter_two_data_b,pptx,Charts,eval,0.005,False,15,105.45, pptarena_case_32_arrange_image_and_text,pptx,Images & Pictures,eval,0.005,False,15,120.04, pptarena_case_36_add_speaker_notes,pptx,Slide/Section Management & Footers,eval,0.005,False,15,86.1, pptarena_case_49_normalize_thousand_separators,pptx,Tables,eval,0.001,False,2,7.38, pptarena_case_35_structural_fix,pptx,Text & Typography,eval,0.001,False,14,88.28, pptarena_case_40_hindu_center_titles,pptx,Text & Typography,eval,0.001,False,5,23.51, pptarena_case_26_match_slide_colors_to_theme,pptx,Theme & Background,eval,0.001,False,2,14.3, finch_10,xlsx,Calculation,eval,0.001,False,9,216.9,empty_response finch_35,xlsx,Calculation,eval,0.001,False,4,38.16, finch_38,xlsx,Calculation,eval,0.001,False,4,24.1, finch_112,xlsx,Cross-sheet/file Retrieval,eval,0.005,False,15,150.87, finch_154,xlsx,Data Entry / Import,eval,0.005,False,15,118.7, finch_14,xlsx,Financial Modeling,eval,0.005,False,15,156.6, finch_168,xlsx,Structuring / Formatting,eval,0.001,False,2,8.83, finch_59,xlsx,Structuring / Formatting,eval,0.001,False,2,7.58, finch_122,xlsx,Summary / Visualization,eval,0.005,False,15,190.28, finch_158,xlsx,Validation / Review,eval,0.005,False,15,100.03,