1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
|
{
"edges": [
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestTestGetInformation::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestTestGetInformation::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestSynthesizeInfo::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestSynthesizeInfo::test_method[challenge_data0]"
}
],
"nodes": [
{
"color": "grey",
"data": {
"category": [
"general",
"coding",
"scrape_synthesize",
"data"
],
"cutoff": 60,
"dependencies": [
"TestWriteFile"
],
"eval_id": "f219f3d3-a41b-45a9-a3d0-389832086ee8",
"ground": {
"answer": "The content of output.txt should be 'Hello World!'",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"Hello World!"
]
},
"info": {
"description": "Tests if the agent can read a file.",
"difficulty": "interface",
"side_effects": [
""
]
},
"name": "TestReadFile",
"task": "Read the file called file_to_read.txt and write its content to a file called output.txt"
},
"id": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"label": "ReadFile",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"general",
"coding",
"scrape_synthesize",
"data"
],
"cutoff": 60,
"dependencies": [],
"eval_id": "021c695a-6cc4-46c2-b93a-f3a9b0f4d123",
"ground": {
"answer": "The word 'Washington', printed to a .txt file named anything",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"Washington"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can write a file",
"difficulty": "interface",
"side_effects": [
""
]
},
"name": "TestWriteFile",
"task": "Write the word 'Washington' to a .txt file"
},
"id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]",
"label": "WriteFile",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"scrape_synthesize",
"general"
],
"cutoff": 60,
"dependencies": [
"TestSearch"
],
"eval_id": "cd96e6b2-779d-4a4a-8367-d520023e27ae",
"ground": {
"answer": "\u00a325.89",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"25.89"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can retrieve a specific information from a website.",
"difficulty": "basic",
"side_effects": []
},
"name": "TestBasicRetrieval",
"task": "Write the price of the book in this url 'http://books.toscrape.com/catalogue/meditations_33/index.html' to a .txt file."
},
"id": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]",
"label": "BasicRetrieval",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"general",
"scrape_synthesize"
],
"cutoff": 120,
"dependencies": [
"TestWriteFile"
],
"eval_id": "0bb23182-b434-402b-a73e-9c226469b959",
"ground": {
"answer": "This is a Heading\nThis is a paragraph.",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"Heading",
"paragraph"
],
"should_not_contain": [
"The",
"the"
]
},
"info": {
"description": "Tests if the agent can search.",
"difficulty": "interface",
"side_effects": [
""
]
},
"name": "TestSearch",
"task": "Open 'https://silennaihin.com/random/plain.html' and paste all of the text on the page in a .txt file"
},
"id": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]",
"label": "Search",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"scrape_synthesize",
"general"
],
"cutoff": 60,
"dependencies": [
"TestRevenueRetrieval2"
],
"eval_id": "1758058c-f726-484f-96fa-f05e278e5ff5",
"ground": {
"answer": "The twitter handles of the two hosts of Latent Space.",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"swyx",
"FanaHOVA"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can retrieve twitter handles given a vague description.",
"difficulty": "intermediate",
"side_effects": [
""
]
},
"name": "TestTestGetInformation",
"task": "Write the twitter handle of the two hosts of Latent Space to a file called output.txt"
},
"id": "agbenchmark/generate_test.py::TestTestGetInformation::test_method[challenge_data0]",
"label": "TestGetInformation",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"scrape_synthesize"
],
"cutoff": 60,
"dependencies": [
"TestRevenueRetrieval"
],
"eval_id": "552bdf23-db40-4bd1-b123-4ed820886cc1",
"ground": {
"answer": "15 Millions\n112 Millions\n117 Millions\n204 Millions\n413 Millions\n2,014 Millions\n3,198 Millions\n4,046 Millions\n7,000 Millions\n11,759 Millions\n21,461 Millions\n24,578 Millions\n31,536 Millions\n53,823 Millions\n81,462 Millions",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"15",
"112",
"117",
"204",
"413",
"2,014",
"3,198",
"4,046",
"7,000",
"11,759",
"21,461",
"24,578",
"31,536",
"53,823",
"81,462"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can retrieve all the revenues of Tesla since its creation.",
"difficulty": "intermediate",
"side_effects": [
"tests if there is in fact an LLM attached"
]
},
"name": "TestRevenueRetrieval2",
"task": "Write tesla's revenue every year since its creation into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 million)."
},
"id": "agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]",
"label": "RevenueRetrieval2",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"scrape_synthesize",
"general"
],
"cutoff": 60,
"dependencies": [
"TestBasicRetrieval"
],
"eval_id": "dc2114d7-1597-4c9b-bed0-a97937ad977f",
"ground": {
"answer": "It was $81.462 billion in 2022. In millions the answer is 81,462.",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"81,462"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can retrieve Tesla's revenue in 2022.",
"difficulty": "intermediate",
"side_effects": []
},
"name": "TestRevenueRetrieval",
"task": "Write tesla's exact revenue in 2022 into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 million)."
},
"id": "agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]",
"label": "RevenueRetrieval",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"scrape_synthesize",
"general"
],
"cutoff": 240,
"dependencies": [
"TestReadFile"
],
"eval_id": "895ae28a-4513-44ea-a872-0164771d1597",
"ground": {
"answer": "A report highlighting elements from the 2 files.",
"eval": {
"scoring": "binary",
"template": "question",
"type": "llm"
},
"files": [
"output.txt"
],
"should_contain": [
"Is the company mentioned in the output actively addressing or capitalizing on the challenges or trends listed?"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can generate content based on the content of 2 files.",
"difficulty": "basic",
"side_effects": []
},
"name": "TestSynthesizeInfo",
"task": "Create a brief report or summary highlighting how one or more companies from companies.txt are addressing or capitalizing on challenges or trends from challenges.txt. Write a file called output.txt."
},
"id": "agbenchmark/generate_test.py::TestSynthesizeInfo::test_method[challenge_data0]",
"label": "SynthesizeInfo",
"shape": "dot"
}
]
}
|
