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)
46167
uvx harbor run -d spreadsheetbench-verified@1.0 -t 461670ad7209
46240
uvx harbor run -d spreadsheetbench-verified@1.0 -t 462400ad7209
463-17
uvx harbor run -d spreadsheetbench-verified@1.0 -t 463-170ad7209
46646
uvx harbor run -d spreadsheetbench-verified@1.0 -t 466460ad7209
46897
uvx harbor run -d spreadsheetbench-verified@1.0 -t 468970ad7209
469-9
uvx harbor run -d spreadsheetbench-verified@1.0 -t 469-90ad7209
4714
uvx harbor run -d spreadsheetbench-verified@1.0 -t 47140ad7209
472-15
uvx harbor run -d spreadsheetbench-verified@1.0 -t 472-150ad7209
477-45
uvx harbor run -d spreadsheetbench-verified@1.0 -t 477-450ad7209
47766
uvx harbor run -d spreadsheetbench-verified@1.0 -t 477660ad7209
47798
uvx harbor run -d spreadsheetbench-verified@1.0 -t 477980ad7209
47827
uvx harbor run -d spreadsheetbench-verified@1.0 -t 478270ad7209
47842
uvx harbor run -d spreadsheetbench-verified@1.0 -t 478420ad7209
47933
uvx harbor run -d spreadsheetbench-verified@1.0 -t 479330ad7209
48080
uvx harbor run -d spreadsheetbench-verified@1.0 -t 480800ad7209
48257
uvx harbor run -d spreadsheetbench-verified@1.0 -t 482570ad7209
48365
uvx harbor run -d spreadsheetbench-verified@1.0 -t 483650ad7209
48527
uvx harbor run -d spreadsheetbench-verified@1.0 -t 485270ad7209
48588
uvx harbor run -d spreadsheetbench-verified@1.0 -t 485880ad7209
486-17
uvx harbor run -d spreadsheetbench-verified@1.0 -t 486-170ad7209
48608
uvx harbor run -d spreadsheetbench-verified@1.0 -t 486080ad7209
48620
uvx harbor run -d spreadsheetbench-verified@1.0 -t 486200ad7209
48643
uvx harbor run -d spreadsheetbench-verified@1.0 -t 486430ad7209
48745
uvx harbor run -d spreadsheetbench-verified@1.0 -t 487450ad7209
488-14
uvx harbor run -d spreadsheetbench-verified@1.0 -t 488-140ad7209
48921
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489210ad7209
48924
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489240ad7209
48969
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489690ad7209
48975
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489750ad7209
48982
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489820ad7209
48983
uvx harbor run -d spreadsheetbench-verified@1.0 -t 489830ad7209
49036
uvx harbor run -d spreadsheetbench-verified@1.0 -t 490360ad7209
49196
uvx harbor run -d spreadsheetbench-verified@1.0 -t 491960ad7209
49237
uvx harbor run -d spreadsheetbench-verified@1.0 -t 492370ad7209
493-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 493-180ad7209
493-5
uvx harbor run -d spreadsheetbench-verified@1.0 -t 493-50ad7209
49300
uvx harbor run -d spreadsheetbench-verified@1.0 -t 493000ad7209
49333
uvx harbor run -d spreadsheetbench-verified@1.0 -t 493330ad7209
496-15
uvx harbor run -d spreadsheetbench-verified@1.0 -t 496-150ad7209
496-34
uvx harbor run -d spreadsheetbench-verified@1.0 -t 496-340ad7209
49667
uvx harbor run -d spreadsheetbench-verified@1.0 -t 496670ad7209
49801
uvx harbor run -d spreadsheetbench-verified@1.0 -t 498010ad7209
49857
uvx harbor run -d spreadsheetbench-verified@1.0 -t 498570ad7209
49945
uvx harbor run -d spreadsheetbench-verified@1.0 -t 499450ad7209
50051
uvx harbor run -d spreadsheetbench-verified@1.0 -t 500510ad7209
50088
uvx harbor run -d spreadsheetbench-verified@1.0 -t 500880ad7209
50193
uvx harbor run -d spreadsheetbench-verified@1.0 -t 501930ad7209
50250
uvx harbor run -d spreadsheetbench-verified@1.0 -t 502500ad7209
50324
uvx harbor run -d spreadsheetbench-verified@1.0 -t 503240ad7209
50486
uvx harbor run -d spreadsheetbench-verified@1.0 -t 504860ad7209
50521
uvx harbor run -d spreadsheetbench-verified@1.0 -t 505210ad7209
50526
uvx harbor run -d spreadsheetbench-verified@1.0 -t 505260ad7209
50631
uvx harbor run -d spreadsheetbench-verified@1.0 -t 506310ad7209
50682
uvx harbor run -d spreadsheetbench-verified@1.0 -t 506820ad7209
50683
uvx harbor run -d spreadsheetbench-verified@1.0 -t 506830ad7209
50768
uvx harbor run -d spreadsheetbench-verified@1.0 -t 507680ad7209
50796
uvx harbor run -d spreadsheetbench-verified@1.0 -t 507960ad7209
50811
uvx harbor run -d spreadsheetbench-verified@1.0 -t 508110ad7209
50916
uvx harbor run -d spreadsheetbench-verified@1.0 -t 509160ad7209
50952
uvx harbor run -d spreadsheetbench-verified@1.0 -t 509520ad7209
50971
uvx harbor run -d spreadsheetbench-verified@1.0 -t 509710ad7209
51-12
uvx harbor run -d spreadsheetbench-verified@1.0 -t 51-120ad7209
510-3
uvx harbor run -d spreadsheetbench-verified@1.0 -t 510-30ad7209
51090
uvx harbor run -d spreadsheetbench-verified@1.0 -t 510900ad7209
51249
uvx harbor run -d spreadsheetbench-verified@1.0 -t 512490ad7209
51262
uvx harbor run -d spreadsheetbench-verified@1.0 -t 512620ad7209
51289
uvx harbor run -d spreadsheetbench-verified@1.0 -t 512890ad7209
51354
uvx harbor run -d spreadsheetbench-verified@1.0 -t 513540ad7209
51359
uvx harbor run -d spreadsheetbench-verified@1.0 -t 513590ad7209
51431
uvx harbor run -d spreadsheetbench-verified@1.0 -t 514310ad7209
51556
uvx harbor run -d spreadsheetbench-verified@1.0 -t 515560ad7209
51586
uvx harbor run -d spreadsheetbench-verified@1.0 -t 515860ad7209
516-46
uvx harbor run -d spreadsheetbench-verified@1.0 -t 516-460ad7209
51680
uvx harbor run -d spreadsheetbench-verified@1.0 -t 516800ad7209
52050
uvx harbor run -d spreadsheetbench-verified@1.0 -t 520500ad7209
52216
uvx harbor run -d spreadsheetbench-verified@1.0 -t 522160ad7209
52220
uvx harbor run -d spreadsheetbench-verified@1.0 -t 522200ad7209
52233
uvx harbor run -d spreadsheetbench-verified@1.0 -t 522330ad7209
52305
uvx harbor run -d spreadsheetbench-verified@1.0 -t 523050ad7209
524-31
uvx harbor run -d spreadsheetbench-verified@1.0 -t 524-310ad7209
52532
uvx harbor run -d spreadsheetbench-verified@1.0 -t 525320ad7209
52541
uvx harbor run -d spreadsheetbench-verified@1.0 -t 525410ad7209
52575
uvx harbor run -d spreadsheetbench-verified@1.0 -t 525750ad7209
52807
uvx harbor run -d spreadsheetbench-verified@1.0 -t 528070ad7209
52917
uvx harbor run -d spreadsheetbench-verified@1.0 -t 529170ad7209
52964
uvx harbor run -d spreadsheetbench-verified@1.0 -t 529640ad7209
531-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 531-180ad7209
53117
uvx harbor run -d spreadsheetbench-verified@1.0 -t 531170ad7209
53161
uvx harbor run -d spreadsheetbench-verified@1.0 -t 531610ad7209
53167
uvx harbor run -d spreadsheetbench-verified@1.0 -t 531670ad7209
53383
uvx harbor run -d spreadsheetbench-verified@1.0 -t 533830ad7209
534-26
uvx harbor run -d spreadsheetbench-verified@1.0 -t 534-260ad7209
53449
uvx harbor run -d spreadsheetbench-verified@1.0 -t 534490ad7209
535-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 535-200ad7209
53647
uvx harbor run -d spreadsheetbench-verified@1.0 -t 536470ad7209
53994
uvx harbor run -d spreadsheetbench-verified@1.0 -t 539940ad7209
54085
uvx harbor run -d spreadsheetbench-verified@1.0 -t 540850ad7209
54144
uvx harbor run -d spreadsheetbench-verified@1.0 -t 541440ad7209
54196
uvx harbor run -d spreadsheetbench-verified@1.0 -t 541960ad7209
54242
uvx harbor run -d spreadsheetbench-verified@1.0 -t 542420ad7209