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)
10452
uvx harbor run -d spreadsheetbench-verified@1.0 -t 104520ad7209
105-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 105-240ad7209
10747
uvx harbor run -d spreadsheetbench-verified@1.0 -t 107470ad7209
108-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 108-240ad7209
109-21
uvx harbor run -d spreadsheetbench-verified@1.0 -t 109-210ad7209
11276
uvx harbor run -d spreadsheetbench-verified@1.0 -t 112760ad7209
118-50
uvx harbor run -d spreadsheetbench-verified@1.0 -t 118-500ad7209
11842
uvx harbor run -d spreadsheetbench-verified@1.0 -t 118420ad7209
120-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 120-240ad7209
12307
uvx harbor run -d spreadsheetbench-verified@1.0 -t 123070ad7209
12864
uvx harbor run -d spreadsheetbench-verified@1.0 -t 128640ad7209
13-1
uvx harbor run -d spreadsheetbench-verified@1.0 -t 13-10ad7209
130-9
uvx harbor run -d spreadsheetbench-verified@1.0 -t 130-90ad7209
13284
uvx harbor run -d spreadsheetbench-verified@1.0 -t 132840ad7209
141-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 141-200ad7209
142-12
uvx harbor run -d spreadsheetbench-verified@1.0 -t 142-120ad7209
142-19
uvx harbor run -d spreadsheetbench-verified@1.0 -t 142-190ad7209
14240
uvx harbor run -d spreadsheetbench-verified@1.0 -t 142400ad7209
146-49
uvx harbor run -d spreadsheetbench-verified@1.0 -t 146-490ad7209
147-48
uvx harbor run -d spreadsheetbench-verified@1.0 -t 147-480ad7209
15380
uvx harbor run -d spreadsheetbench-verified@1.0 -t 153800ad7209
15387
uvx harbor run -d spreadsheetbench-verified@1.0 -t 153870ad7209
156-14
uvx harbor run -d spreadsheetbench-verified@1.0 -t 156-140ad7209
1563
uvx harbor run -d spreadsheetbench-verified@1.0 -t 15630ad7209
15671
uvx harbor run -d spreadsheetbench-verified@1.0 -t 156710ad7209
157-4
uvx harbor run -d spreadsheetbench-verified@1.0 -t 157-40ad7209
160-6
uvx harbor run -d spreadsheetbench-verified@1.0 -t 160-60ad7209
165-23
uvx harbor run -d spreadsheetbench-verified@1.0 -t 165-230ad7209
16511
uvx harbor run -d spreadsheetbench-verified@1.0 -t 165110ad7209
168-17
uvx harbor run -d spreadsheetbench-verified@1.0 -t 168-170ad7209
17-35
uvx harbor run -d spreadsheetbench-verified@1.0 -t 17-350ad7209
170-13
uvx harbor run -d spreadsheetbench-verified@1.0 -t 170-130ad7209
17111
uvx harbor run -d spreadsheetbench-verified@1.0 -t 171110ad7209
177-6
uvx harbor run -d spreadsheetbench-verified@1.0 -t 177-60ad7209
178-22
uvx harbor run -d spreadsheetbench-verified@1.0 -t 178-220ad7209
1818
uvx harbor run -d spreadsheetbench-verified@1.0 -t 18180ad7209
183-8
uvx harbor run -d spreadsheetbench-verified@1.0 -t 183-80ad7209
18645
uvx harbor run -d spreadsheetbench-verified@1.0 -t 186450ad7209
188-39
uvx harbor run -d spreadsheetbench-verified@1.0 -t 188-390ad7209
18935
uvx harbor run -d spreadsheetbench-verified@1.0 -t 189350ad7209
191-40
uvx harbor run -d spreadsheetbench-verified@1.0 -t 191-400ad7209
192-22
uvx harbor run -d spreadsheetbench-verified@1.0 -t 192-220ad7209
1925
uvx harbor run -d spreadsheetbench-verified@1.0 -t 19250ad7209
194-19
uvx harbor run -d spreadsheetbench-verified@1.0 -t 194-190ad7209
203-15
uvx harbor run -d spreadsheetbench-verified@1.0 -t 203-150ad7209
208-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 208-200ad7209
209-30
uvx harbor run -d spreadsheetbench-verified@1.0 -t 209-300ad7209
22-47
uvx harbor run -d spreadsheetbench-verified@1.0 -t 22-470ad7209
227-40
uvx harbor run -d spreadsheetbench-verified@1.0 -t 227-400ad7209
23-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 23-240ad7209
230-16
uvx harbor run -d spreadsheetbench-verified@1.0 -t 230-160ad7209
236-22
uvx harbor run -d spreadsheetbench-verified@1.0 -t 236-220ad7209
24-23
uvx harbor run -d spreadsheetbench-verified@1.0 -t 24-230ad7209
247-24
uvx harbor run -d spreadsheetbench-verified@1.0 -t 247-240ad7209
250-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 250-200ad7209
254-34
uvx harbor run -d spreadsheetbench-verified@1.0 -t 254-340ad7209
262-17
uvx harbor run -d spreadsheetbench-verified@1.0 -t 262-170ad7209
263-1
uvx harbor run -d spreadsheetbench-verified@1.0 -t 263-10ad7209
267-18
uvx harbor run -d spreadsheetbench-verified@1.0 -t 267-180ad7209
267-21
uvx harbor run -d spreadsheetbench-verified@1.0 -t 267-210ad7209
269-43
uvx harbor run -d spreadsheetbench-verified@1.0 -t 269-430ad7209
269-44
uvx harbor run -d spreadsheetbench-verified@1.0 -t 269-440ad7209
2768
uvx harbor run -d spreadsheetbench-verified@1.0 -t 27680ad7209
279-23
uvx harbor run -d spreadsheetbench-verified@1.0 -t 279-230ad7209
28-7
uvx harbor run -d spreadsheetbench-verified@1.0 -t 28-70ad7209
280-17
uvx harbor run -d spreadsheetbench-verified@1.0 -t 280-170ad7209
283-32
uvx harbor run -d spreadsheetbench-verified@1.0 -t 283-320ad7209
290-1
uvx harbor run -d spreadsheetbench-verified@1.0 -t 290-10ad7209
290-27
uvx harbor run -d spreadsheetbench-verified@1.0 -t 290-270ad7209
297-42
uvx harbor run -d spreadsheetbench-verified@1.0 -t 297-420ad7209
3002
uvx harbor run -d spreadsheetbench-verified@1.0 -t 30020ad7209
302-1
uvx harbor run -d spreadsheetbench-verified@1.0 -t 302-10ad7209
304-35
uvx harbor run -d spreadsheetbench-verified@1.0 -t 304-350ad7209
30930
uvx harbor run -d spreadsheetbench-verified@1.0 -t 309300ad7209
31011
uvx harbor run -d spreadsheetbench-verified@1.0 -t 310110ad7209
31202
uvx harbor run -d spreadsheetbench-verified@1.0 -t 312020ad7209
31628
uvx harbor run -d spreadsheetbench-verified@1.0 -t 316280ad7209
31746
uvx harbor run -d spreadsheetbench-verified@1.0 -t 317460ad7209
31915
uvx harbor run -d spreadsheetbench-verified@1.0 -t 319150ad7209
32023
uvx harbor run -d spreadsheetbench-verified@1.0 -t 320230ad7209
32093
uvx harbor run -d spreadsheetbench-verified@1.0 -t 320930ad7209
32255
uvx harbor run -d spreadsheetbench-verified@1.0 -t 322550ad7209
32293
uvx harbor run -d spreadsheetbench-verified@1.0 -t 322930ad7209
32337
uvx harbor run -d spreadsheetbench-verified@1.0 -t 323370ad7209
32438
uvx harbor run -d spreadsheetbench-verified@1.0 -t 324380ad7209
325-44
uvx harbor run -d spreadsheetbench-verified@1.0 -t 325-440ad7209
32562
uvx harbor run -d spreadsheetbench-verified@1.0 -t 325620ad7209
32612
uvx harbor run -d spreadsheetbench-verified@1.0 -t 326120ad7209
32789
uvx harbor run -d spreadsheetbench-verified@1.0 -t 327890ad7209
32902
uvx harbor run -d spreadsheetbench-verified@1.0 -t 329020ad7209
33157
uvx harbor run -d spreadsheetbench-verified@1.0 -t 331570ad7209
333-29
uvx harbor run -d spreadsheetbench-verified@1.0 -t 333-290ad7209
334-11
uvx harbor run -d spreadsheetbench-verified@1.0 -t 334-110ad7209
33722
uvx harbor run -d spreadsheetbench-verified@1.0 -t 337220ad7209
34033
uvx harbor run -d spreadsheetbench-verified@1.0 -t 340330ad7209
341-14
uvx harbor run -d spreadsheetbench-verified@1.0 -t 341-140ad7209
341-40
uvx harbor run -d spreadsheetbench-verified@1.0 -t 341-400ad7209
3413
uvx harbor run -d spreadsheetbench-verified@1.0 -t 34130ad7209
34210
uvx harbor run -d spreadsheetbench-verified@1.0 -t 342100ad7209
343-20
uvx harbor run -d spreadsheetbench-verified@1.0 -t 343-200ad7209