spreadsheetbench-verified
v1.0A benchmark evaluating AI agents on real-world spreadsheet manipulation tasks (400 tasks from verified_400). Tasks involve Excel file manipulation including formula writing, data transformation, formatting, and conditional logic.
uvx harbor run -d spreadsheetbench-verified@1.0Tasks (400)
54274
uvx harbor run -d spreadsheetbench-verified@1.0 -t 542740ad7209
54474
uvx harbor run -d spreadsheetbench-verified@1.0 -t 544740ad7209
545-35
uvx harbor run -d spreadsheetbench-verified@1.0 -t 545-350ad7209
54513
uvx harbor run -d spreadsheetbench-verified@1.0 -t 545130ad7209
54590
uvx harbor run -d spreadsheetbench-verified@1.0 -t 545900ad7209
54638
uvx harbor run -d spreadsheetbench-verified@1.0 -t 546380ad7209
54667
uvx harbor run -d spreadsheetbench-verified@1.0 -t 546670ad7209
54675
uvx harbor run -d spreadsheetbench-verified@1.0 -t 546750ad7209
547-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 547-180ad7209
547-43
uvx harbor run -d spreadsheetbench-verified@1.0 -t 547-430ad7209
54717
uvx harbor run -d spreadsheetbench-verified@1.0 -t 547170ad7209
54925
uvx harbor run -d spreadsheetbench-verified@1.0 -t 549250ad7209
55049
uvx harbor run -d spreadsheetbench-verified@1.0 -t 550490ad7209
55060
uvx harbor run -d spreadsheetbench-verified@1.0 -t 550600ad7209
55085
uvx harbor run -d spreadsheetbench-verified@1.0 -t 550850ad7209
55260
uvx harbor run -d spreadsheetbench-verified@1.0 -t 552600ad7209
55421
uvx harbor run -d spreadsheetbench-verified@1.0 -t 554210ad7209
55427
uvx harbor run -d spreadsheetbench-verified@1.0 -t 554270ad7209
55468
uvx harbor run -d spreadsheetbench-verified@1.0 -t 554680ad7209
55708
uvx harbor run -d spreadsheetbench-verified@1.0 -t 557080ad7209
55817
uvx harbor run -d spreadsheetbench-verified@1.0 -t 558170ad7209
55965
uvx harbor run -d spreadsheetbench-verified@1.0 -t 559650ad7209
55976
uvx harbor run -d spreadsheetbench-verified@1.0 -t 559760ad7209
55977
uvx harbor run -d spreadsheetbench-verified@1.0 -t 559770ad7209
55979
uvx harbor run -d spreadsheetbench-verified@1.0 -t 559790ad7209
560-12
uvx harbor run -d spreadsheetbench-verified@1.0 -t 560-120ad7209
56225
uvx harbor run -d spreadsheetbench-verified@1.0 -t 562250ad7209
56274
uvx harbor run -d spreadsheetbench-verified@1.0 -t 562740ad7209
56378
uvx harbor run -d spreadsheetbench-verified@1.0 -t 563780ad7209
56419
uvx harbor run -d spreadsheetbench-verified@1.0 -t 564190ad7209
56427
uvx harbor run -d spreadsheetbench-verified@1.0 -t 564270ad7209
56563
uvx harbor run -d spreadsheetbench-verified@1.0 -t 565630ad7209
56599
uvx harbor run -d spreadsheetbench-verified@1.0 -t 565990ad7209
567-21
uvx harbor run -d spreadsheetbench-verified@1.0 -t 567-210ad7209
56786
uvx harbor run -d spreadsheetbench-verified@1.0 -t 567860ad7209
56915
uvx harbor run -d spreadsheetbench-verified@1.0 -t 569150ad7209
56920
uvx harbor run -d spreadsheetbench-verified@1.0 -t 569200ad7209
56921
uvx harbor run -d spreadsheetbench-verified@1.0 -t 569210ad7209
56953
uvx harbor run -d spreadsheetbench-verified@1.0 -t 569530ad7209
57033
uvx harbor run -d spreadsheetbench-verified@1.0 -t 570330ad7209
57113
uvx harbor run -d spreadsheetbench-verified@1.0 -t 571130ad7209
57117
uvx harbor run -d spreadsheetbench-verified@1.0 -t 571170ad7209
57232
uvx harbor run -d spreadsheetbench-verified@1.0 -t 572320ad7209
57262
uvx harbor run -d spreadsheetbench-verified@1.0 -t 572620ad7209
57354
uvx harbor run -d spreadsheetbench-verified@1.0 -t 573540ad7209
57445
uvx harbor run -d spreadsheetbench-verified@1.0 -t 574450ad7209
57558
uvx harbor run -d spreadsheetbench-verified@1.0 -t 575580ad7209
57590
uvx harbor run -d spreadsheetbench-verified@1.0 -t 575900ad7209
57612
uvx harbor run -d spreadsheetbench-verified@1.0 -t 576120ad7209
57693
uvx harbor run -d spreadsheetbench-verified@1.0 -t 576930ad7209
577-40
uvx harbor run -d spreadsheetbench-verified@1.0 -t 577-400ad7209
57743
uvx harbor run -d spreadsheetbench-verified@1.0 -t 577430ad7209
57989
uvx harbor run -d spreadsheetbench-verified@1.0 -t 579890ad7209
58032
uvx harbor run -d spreadsheetbench-verified@1.0 -t 580320ad7209
58109
uvx harbor run -d spreadsheetbench-verified@1.0 -t 581090ad7209
58147
uvx harbor run -d spreadsheetbench-verified@1.0 -t 581470ad7209
5835
uvx harbor run -d spreadsheetbench-verified@1.0 -t 58350ad7209
58484
uvx harbor run -d spreadsheetbench-verified@1.0 -t 584840ad7209
58499
uvx harbor run -d spreadsheetbench-verified@1.0 -t 584990ad7209
585-41
uvx harbor run -d spreadsheetbench-verified@1.0 -t 585-410ad7209
58687
uvx harbor run -d spreadsheetbench-verified@1.0 -t 586870ad7209
58701
uvx harbor run -d spreadsheetbench-verified@1.0 -t 587010ad7209
58723
uvx harbor run -d spreadsheetbench-verified@1.0 -t 587230ad7209
58904
uvx harbor run -d spreadsheetbench-verified@1.0 -t 589040ad7209
58942
uvx harbor run -d spreadsheetbench-verified@1.0 -t 589420ad7209
58949
uvx harbor run -d spreadsheetbench-verified@1.0 -t 589490ad7209
59129
uvx harbor run -d spreadsheetbench-verified@1.0 -t 591290ad7209
59160
uvx harbor run -d spreadsheetbench-verified@1.0 -t 591600ad7209
59196
uvx harbor run -d spreadsheetbench-verified@1.0 -t 591960ad7209
59224
uvx harbor run -d spreadsheetbench-verified@1.0 -t 592240ad7209
59358
uvx harbor run -d spreadsheetbench-verified@1.0 -t 593580ad7209
59511
uvx harbor run -d spreadsheetbench-verified@1.0 -t 595110ad7209
59595
uvx harbor run -d spreadsheetbench-verified@1.0 -t 595950ad7209
59639
uvx harbor run -d spreadsheetbench-verified@1.0 -t 596390ad7209
59734
uvx harbor run -d spreadsheetbench-verified@1.0 -t 597340ad7209
59794
uvx harbor run -d spreadsheetbench-verified@1.0 -t 597940ad7209
59884
uvx harbor run -d spreadsheetbench-verified@1.0 -t 598840ad7209
599-9
uvx harbor run -d spreadsheetbench-verified@1.0 -t 599-90ad7209
59902
uvx harbor run -d spreadsheetbench-verified@1.0 -t 599020ad7209
60-7
uvx harbor run -d spreadsheetbench-verified@1.0 -t 60-70ad7209
61-4
uvx harbor run -d spreadsheetbench-verified@1.0 -t 61-40ad7209
6239
uvx harbor run -d spreadsheetbench-verified@1.0 -t 62390ad7209
66-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 66-240ad7209
6698
uvx harbor run -d spreadsheetbench-verified@1.0 -t 66980ad7209
73-45
uvx harbor run -d spreadsheetbench-verified@1.0 -t 73-450ad7209
7665
uvx harbor run -d spreadsheetbench-verified@1.0 -t 76650ad7209
79-7
uvx harbor run -d spreadsheetbench-verified@1.0 -t 79-70ad7209
7902
uvx harbor run -d spreadsheetbench-verified@1.0 -t 79020ad7209
80-42
uvx harbor run -d spreadsheetbench-verified@1.0 -t 80-420ad7209
82-30
uvx harbor run -d spreadsheetbench-verified@1.0 -t 82-300ad7209
82-38
uvx harbor run -d spreadsheetbench-verified@1.0 -t 82-380ad7209
84-40
uvx harbor run -d spreadsheetbench-verified@1.0 -t 84-400ad7209
8942
uvx harbor run -d spreadsheetbench-verified@1.0 -t 89420ad7209
91-34
uvx harbor run -d spreadsheetbench-verified@1.0 -t 91-340ad7209
9111
uvx harbor run -d spreadsheetbench-verified@1.0 -t 91110ad7209
9391
uvx harbor run -d spreadsheetbench-verified@1.0 -t 93910ad7209
9448
uvx harbor run -d spreadsheetbench-verified@1.0 -t 94480ad7209
9569
uvx harbor run -d spreadsheetbench-verified@1.0 -t 95690ad7209
97-36
uvx harbor run -d spreadsheetbench-verified@1.0 -t 97-360ad7209
9726
uvx harbor run -d spreadsheetbench-verified@1.0 -t 97260ad7209