RQ1
Each number inside the following tables links to a JSON list containing the corresponding data. Each element in the JSON list is a piece of code, in the form of a string.
Here is a sample JSON list:
[
"count = 0\nfor i in int_list:\n count += i",
"import numpy as np\ncount = np.sum(int_list)",
"count = sum(int_list)",
.
.
.
]
Please refer Table 1 to find the details of the CPAT Numbers mentioned below.
GPT-3.5
CPAT Number | correct | syntax-errors | type-errors | import-errors | invalid_format | incorrect |
---|---|---|---|---|---|---|
1 | 40 | 0 | 286 | 47 | 0 | 100 |
2 | 102 | 0 | 147 | 14 | 1 | 168 |
3 | 39 | 0 | 0 | 34 | 0 | 327 |
4 | 11 | 0 | 279 | 20 | 1 | 145 |
5 | 100 | 0 | 161 | 32 | 2 | 215 |
6 | 71 | 0 | 242 | 12 | 0 | 169 |
7 | 61 | 0 | 204 | 78 | 0 | 193 |
8 | 18 | 0 | 203 | 62 | 0 | 96 |
9 | 9 | 0 | 158 | 27 | 2 | 281 |
10 | 100 | 0 | 45 | 43 | 0 | 295 |
11 | 150 | 0 | 63 | 81 | 0 | 230 |
12 | 97 | 0 | 254 | 67 | 0 | 64 |
13 | 0 | 0 | 0 | 316 | 2 | 123 |
14 | 11 | 0 | 0 | 83 | 0 | 343 |
15 | 77 | 0 | 0 | 32 | 1 | 276 |
16 | 69 | 0 | 0 | 10 | 1 | 327 |
17 | 109 | 0 | 0 | 9 | 0 | 333 |
18 | 39 | 0 | 0 | 57 | 0 | 369 |
19 | 20 | 0 | 127 | 11 | 0 | 407 |
20 | 136 | 0 | 0 | 2 | 2 | 296 |
GPT-4
CPAT Number | correct | syntax-errors | type-errors | import-errors | invalid_format | incorrect |
---|---|---|---|---|---|---|
1 | 67 | 0 | 159 | 27 | 0 | 116 |
2 | 187 | 0 | 45 | 15 | 0 | 162 |
3 | 58 | 0 | 0 | 18 | 1 | 268 |
4 | 101 | 0 | 150 | 18 | 0 | 114 |
5 | 132 | 0 | 107 | 26 | 2 | 192 |
6 | 161 | 0 | 113 | 27 | 0 | 136 |
7 | 53 | 0 | 229 | 10 | 3 | 103 |
8 | 21 | 0 | 210 | 27 | 0 | 89 |
9 | 15 | 0 | 165 | 31 | 1 | 135 |
10 | 184 | 0 | 30 | 23 | 0 | 196 |
11 | 115 | 0 | 37 | 31 | 0 | 252 |
12 | 98 | 0 | 274 | 20 | 0 | 11 |
13 | 0 | 0 | 0 | 312 | 0 | 106 |
14 | 272 | 0 | 0 | 16 | 0 | 152 |
15 | 132 | 0 | 0 | 20 | 3 | 293 |
16 | 224 | 0 | 0 | 7 | 20 | 119 |
17 | 101 | 0 | 0 | 6 | 0 | 271 |
18 | 166 | 0 | 0 | 9 | 3 | 219 |
19 | 144 | 0 | 52 | 16 | 0 | 153 |
20 | 153 | 0 | 0 | 23 | 0 | 247 |
PALM
CPAT Number | correct | syntax-errors | type-errors | import-errors | invalid_format | incorrect |
---|---|---|---|---|---|---|
1 | 27 | 123 | 154 | 61 | 0 | 133 |
2 | 36 | 68 | 177 | 29 | 0 | 195 |
3 | 18 | 11 | 0 | 116 | 0 | 370 |
4 | 3 | 26 | 172 | 10 | 0 | 233 |
5 | 34 | 38 | 166 | 115 | 0 | 159 |
6 | 40 | 35 | 41 | 141 | 0 | 256 |
7 | 21 | 36 | 94 | 121 | 0 | 135 |
8 | 12 | 114 | 130 | 111 | 0 | 128 |
9 | 13 | 43 | 137 | 65 | 0 | 139 |
10 | 32 | 3 | 82 | 81 | 0 | 332 |
11 | 7 | 66 | 36 | 254 | 0 | 164 |
12 | 29 | 92 | 132 | 184 | 0 | 96 |
13 | 0 | 27 | 0 | 357 | 0 | 91 |
14 | 18 | 42 | 0 | 104 | 0 | 329 |
15 | 10 | 86 | 0 | 36 | 0 | 253 |
16 | 34 | 53 | 0 | 56 | 0 | 324 |
17 | 31 | 31 | 0 | 38 | 0 | 439 |
18 | 71 | 49 | 0 | 26 | 0 | 341 |
19 | 0 | 107 | 225 | 169 | 0 | 70 |
20 | 25 | 39 | 0 | 4 | 0 | 422 |