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)
353-29
uvx harbor run -d spreadsheetbench-verified@1.0 -t 353-290ad7209
353-6
uvx harbor run -d spreadsheetbench-verified@1.0 -t 353-60ad7209
35739
uvx harbor run -d spreadsheetbench-verified@1.0 -t 357390ad7209
35742
uvx harbor run -d spreadsheetbench-verified@1.0 -t 357420ad7209
35747
uvx harbor run -d spreadsheetbench-verified@1.0 -t 357470ad7209
359-21
uvx harbor run -d spreadsheetbench-verified@1.0 -t 359-210ad7209
36097
uvx harbor run -d spreadsheetbench-verified@1.0 -t 360970ad7209
36191
uvx harbor run -d spreadsheetbench-verified@1.0 -t 361910ad7209
36277
uvx harbor run -d spreadsheetbench-verified@1.0 -t 362770ad7209
367-23
uvx harbor run -d spreadsheetbench-verified@1.0 -t 367-230ad7209
36764
uvx harbor run -d spreadsheetbench-verified@1.0 -t 367640ad7209
370-43
uvx harbor run -d spreadsheetbench-verified@1.0 -t 370-430ad7209
37086
uvx harbor run -d spreadsheetbench-verified@1.0 -t 370860ad7209
37229
uvx harbor run -d spreadsheetbench-verified@1.0 -t 372290ad7209
37378
uvx harbor run -d spreadsheetbench-verified@1.0 -t 373780ad7209
374-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 374-180ad7209
374-31
uvx harbor run -d spreadsheetbench-verified@1.0 -t 374-310ad7209
37456
uvx harbor run -d spreadsheetbench-verified@1.0 -t 374560ad7209
37462
uvx harbor run -d spreadsheetbench-verified@1.0 -t 374620ad7209
37554
uvx harbor run -d spreadsheetbench-verified@1.0 -t 375540ad7209
379-36
uvx harbor run -d spreadsheetbench-verified@1.0 -t 379-360ad7209
37900
uvx harbor run -d spreadsheetbench-verified@1.0 -t 379000ad7209
38074
uvx harbor run -d spreadsheetbench-verified@1.0 -t 380740ad7209
382-10
uvx harbor run -d spreadsheetbench-verified@1.0 -t 382-100ad7209
382-29
uvx harbor run -d spreadsheetbench-verified@1.0 -t 382-290ad7209
384-4
uvx harbor run -d spreadsheetbench-verified@1.0 -t 384-40ad7209
38462
uvx harbor run -d spreadsheetbench-verified@1.0 -t 384620ad7209
38537
uvx harbor run -d spreadsheetbench-verified@1.0 -t 385370ad7209
387-16
uvx harbor run -d spreadsheetbench-verified@1.0 -t 387-160ad7209
38703
uvx harbor run -d spreadsheetbench-verified@1.0 -t 387030ad7209
388-47
uvx harbor run -d spreadsheetbench-verified@1.0 -t 388-470ad7209
38823
uvx harbor run -d spreadsheetbench-verified@1.0 -t 388230ad7209
38969
uvx harbor run -d spreadsheetbench-verified@1.0 -t 389690ad7209
38985
uvx harbor run -d spreadsheetbench-verified@1.0 -t 389850ad7209
39046
uvx harbor run -d spreadsheetbench-verified@1.0 -t 390460ad7209
3911
uvx harbor run -d spreadsheetbench-verified@1.0 -t 39110ad7209
39190
uvx harbor run -d spreadsheetbench-verified@1.0 -t 391900ad7209
39432
uvx harbor run -d spreadsheetbench-verified@1.0 -t 394320ad7209
395-36
uvx harbor run -d spreadsheetbench-verified@1.0 -t 395-360ad7209
39515
uvx harbor run -d spreadsheetbench-verified@1.0 -t 395150ad7209
39667
uvx harbor run -d spreadsheetbench-verified@1.0 -t 396670ad7209
398-14
uvx harbor run -d spreadsheetbench-verified@1.0 -t 398-140ad7209
399-14
uvx harbor run -d spreadsheetbench-verified@1.0 -t 399-140ad7209
39903
uvx harbor run -d spreadsheetbench-verified@1.0 -t 399030ad7209
39931
uvx harbor run -d spreadsheetbench-verified@1.0 -t 399310ad7209
402-43
uvx harbor run -d spreadsheetbench-verified@1.0 -t 402-430ad7209
40478
uvx harbor run -d spreadsheetbench-verified@1.0 -t 404780ad7209
40757
uvx harbor run -d spreadsheetbench-verified@1.0 -t 407570ad7209
408-39
uvx harbor run -d spreadsheetbench-verified@1.0 -t 408-390ad7209
408-5
uvx harbor run -d spreadsheetbench-verified@1.0 -t 408-50ad7209
40892
uvx harbor run -d spreadsheetbench-verified@1.0 -t 408920ad7209
409-45
uvx harbor run -d spreadsheetbench-verified@1.0 -t 409-450ad7209
40959
uvx harbor run -d spreadsheetbench-verified@1.0 -t 409590ad7209
41-47
uvx harbor run -d spreadsheetbench-verified@1.0 -t 41-470ad7209
41265
uvx harbor run -d spreadsheetbench-verified@1.0 -t 412650ad7209
41348
uvx harbor run -d spreadsheetbench-verified@1.0 -t 413480ad7209
414-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 414-200ad7209
41410
uvx harbor run -d spreadsheetbench-verified@1.0 -t 414100ad7209
41420
uvx harbor run -d spreadsheetbench-verified@1.0 -t 414200ad7209
41589
uvx harbor run -d spreadsheetbench-verified@1.0 -t 415890ad7209
416-15
uvx harbor run -d spreadsheetbench-verified@1.0 -t 416-150ad7209
416-27
uvx harbor run -d spreadsheetbench-verified@1.0 -t 416-270ad7209
41601
uvx harbor run -d spreadsheetbench-verified@1.0 -t 416010ad7209
41691
uvx harbor run -d spreadsheetbench-verified@1.0 -t 416910ad7209
41969
uvx harbor run -d spreadsheetbench-verified@1.0 -t 419690ad7209
41978
uvx harbor run -d spreadsheetbench-verified@1.0 -t 419780ad7209
42181
uvx harbor run -d spreadsheetbench-verified@1.0 -t 421810ad7209
42198
uvx harbor run -d spreadsheetbench-verified@1.0 -t 421980ad7209
42216
uvx harbor run -d spreadsheetbench-verified@1.0 -t 422160ad7209
423-16
uvx harbor run -d spreadsheetbench-verified@1.0 -t 423-160ad7209
42354
uvx harbor run -d spreadsheetbench-verified@1.0 -t 423540ad7209
42515
uvx harbor run -d spreadsheetbench-verified@1.0 -t 425150ad7209
42526
uvx harbor run -d spreadsheetbench-verified@1.0 -t 425260ad7209
42902
uvx harbor run -d spreadsheetbench-verified@1.0 -t 429020ad7209
42930
uvx harbor run -d spreadsheetbench-verified@1.0 -t 429300ad7209
43213
uvx harbor run -d spreadsheetbench-verified@1.0 -t 432130ad7209
433-47
uvx harbor run -d spreadsheetbench-verified@1.0 -t 433-470ad7209
43436
uvx harbor run -d spreadsheetbench-verified@1.0 -t 434360ad7209
43589
uvx harbor run -d spreadsheetbench-verified@1.0 -t 435890ad7209
43657
uvx harbor run -d spreadsheetbench-verified@1.0 -t 436570ad7209
438-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 438-180ad7209
440-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 440-240ad7209
44017
uvx harbor run -d spreadsheetbench-verified@1.0 -t 440170ad7209
44266
uvx harbor run -d spreadsheetbench-verified@1.0 -t 442660ad7209
44296
uvx harbor run -d spreadsheetbench-verified@1.0 -t 442960ad7209
44389
uvx harbor run -d spreadsheetbench-verified@1.0 -t 443890ad7209
44628
uvx harbor run -d spreadsheetbench-verified@1.0 -t 446280ad7209
448-11
uvx harbor run -d spreadsheetbench-verified@1.0 -t 448-110ad7209
44913
uvx harbor run -d spreadsheetbench-verified@1.0 -t 449130ad7209
45063
uvx harbor run -d spreadsheetbench-verified@1.0 -t 450630ad7209
45300
uvx harbor run -d spreadsheetbench-verified@1.0 -t 453000ad7209
45372
uvx harbor run -d spreadsheetbench-verified@1.0 -t 453720ad7209
455-35
uvx harbor run -d spreadsheetbench-verified@1.0 -t 455-350ad7209
45635
uvx harbor run -d spreadsheetbench-verified@1.0 -t 456350ad7209
45707
uvx harbor run -d spreadsheetbench-verified@1.0 -t 457070ad7209
45738
uvx harbor run -d spreadsheetbench-verified@1.0 -t 457380ad7209
45896
uvx harbor run -d spreadsheetbench-verified@1.0 -t 458960ad7209
45937
uvx harbor run -d spreadsheetbench-verified@1.0 -t 459370ad7209
45944
uvx harbor run -d spreadsheetbench-verified@1.0 -t 459440ad7209
46121
uvx harbor run -d spreadsheetbench-verified@1.0 -t 461210ad7209