prompt stringlengths 1.5k 5.3k | responses listlengths 16 16 | abstractions listlengths 4 4 | train stringclasses 60
values | test stringclasses 60
values | source stringclasses 4
values | answer stringclasses 60
values | num_tokens int64 548 3.83k | cheatsheet stringlengths 0 736 ⌀ | avg_hamming_distance float64 0 626 | avg_percentage_match float64 0 1 | avg_is_correct float64 0 1 | hamming_distances listlengths 16 16 | percentage_matches listlengths 16 16 | is_corrects listlengths 16 16 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. There are three examples gi(...TRUNCATED) | ["Think of each input cell as being “blown up” into a little solid square in the output. Check (...TRUNCATED) | "[{\"input\": [[2, 2, 9, 5, 2, 2, 2, 1], [0, 2, 3, 0, 2, 2, 2, 6]], \"output\": [[2, 2, 2, 2, 2, 2, (...TRUNCATED) | "[{\"input\": [[6, 2, 6, 2, 2, 6, 2, 2, 6], [2, 6, 6, 6, 2, 2, 2, 2, 6], [2, 2, 2, 6, 2, 2, 2, 6, 2](...TRUNCATED) | rearc | "```\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2(...TRUNCATED) | 2,792 | "Think of each input cell as being “blown up” into a little solid square in the output. Check o(...TRUNCATED) | 567 | 0 | 0 | [
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567,
567
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. The problem says that in ea(...TRUNCATED) | ["Think of each input cell as being “blown up” into a little solid square in the output. Check (...TRUNCATED) | "[{\"input\": [[2, 2, 9, 5, 2, 2, 2, 1], [0, 2, 3, 0, 2, 2, 2, 6]], \"output\": [[2, 2, 2, 2, 2, 2, (...TRUNCATED) | "[{\"input\": [[6, 2, 6, 2, 2, 6, 2, 2, 6], [2, 6, 6, 6, 2, 2, 2, 2, 6], [2, 2, 2, 6, 2, 2, 2, 6, 2](...TRUNCATED) | rearc | "```\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2(...TRUNCATED) | 2,792 | "Notice that in each example the output’s width and height are exactly three times the input’s, (...TRUNCATED) | 354.375 | 0.375 | 0.375 | [
567,
567,
0,
567,
0,
567,
567,
567,
567,
0,
0,
0,
567,
567,
567,
0
] | [
0,
0,
1,
0,
1,
0,
0,
0,
0,
1,
1,
1,
0,
0,
0,
1
] | [
false,
false,
true,
false,
true,
false,
false,
false,
false,
true,
true,
true,
false,
false,
false,
true
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples to apply to the test input. (...TRUNCATED) | ["Think of each input cell as being “blown up” into a little solid square in the output. Check (...TRUNCATED) | "[{\"input\": [[2, 2, 9, 5, 2, 2, 2, 1], [0, 2, 3, 0, 2, 2, 2, 6]], \"output\": [[2, 2, 2, 2, 2, 2, (...TRUNCATED) | "[{\"input\": [[6, 2, 6, 2, 2, 6, 2, 2, 6], [2, 6, 6, 6, 2, 2, 2, 2, 6], [2, 2, 2, 6, 2, 2, 2, 6, 2](...TRUNCATED) | rearc | "```\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2(...TRUNCATED) | 2,792 | "Think about how many output cells correspond to a single input cell. In every example each origina(...TRUNCATED) | 496.125 | 0.125 | 0.125 | [
567,
0,
567,
567,
567,
567,
0,
567,
567,
567,
567,
567,
567,
567,
567,
567
] | [
0,
1,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
true,
false,
false,
false,
false,
true,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. The problem says that each (...TRUNCATED) | ["Think of each input cell as being “blown up” into a little solid square in the output. Check (...TRUNCATED) | "[{\"input\": [[2, 2, 9, 5, 2, 2, 2, 1], [0, 2, 3, 0, 2, 2, 2, 6]], \"output\": [[2, 2, 2, 2, 2, 2, (...TRUNCATED) | "[{\"input\": [[6, 2, 6, 2, 2, 6, 2, 2, 6], [2, 6, 6, 6, 2, 2, 2, 2, 6], [2, 2, 2, 6, 2, 2, 2, 6, 2](...TRUNCATED) | rearc | "```\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2(...TRUNCATED) | 2,792 | "Think about how the output’s dimensions relate to the input’s. You’ll see each input cell tu(...TRUNCATED) | 354.9375 | 0.374008 | 0.3125 | [
567,
0,
567,
567,
567,
567,
567,
0,
567,
0,
0,
567,
567,
567,
0,
9
] | [
0,
1,
0,
0,
0,
0,
0,
1,
0,
1,
1,
0,
0,
0,
1,
0.9841269841269841
] | [
false,
true,
false,
false,
false,
false,
false,
true,
false,
true,
true,
false,
false,
false,
true,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. There are three examples gi(...TRUNCATED) | ["Think of each input cell as being “blown up” into a little solid square in the output. Check (...TRUNCATED) | "[{\"input\": [[2, 2, 9, 5, 2, 2, 2, 1], [0, 2, 3, 0, 2, 2, 2, 6]], \"output\": [[2, 2, 2, 2, 2, 2, (...TRUNCATED) | "[{\"input\": [[6, 2, 6, 2, 2, 6, 2, 2, 6], [2, 6, 6, 6, 2, 2, 2, 2, 6], [2, 2, 2, 6, 2, 2, 2, 6, 2](...TRUNCATED) | rearc | "```\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6\n6 6 6 2 2 2 6 6 6 2 2 2 2 2 2 6 6 6 2 2(...TRUNCATED) | 2,792 | null | 496.125 | 0.125 | 0.125 | [
567,
0,
567,
567,
567,
567,
0,
567,
567,
567,
567,
567,
567,
567,
567,
567
] | [
0,
1,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
true,
false,
false,
false,
false,
true,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. The hint says: \"First isol(...TRUNCATED) | ["Hint: First isolate each connected same‐color region in the input. In the output you’ll find t(...TRUNCATED) | "[{\"input\": [[7, 7, 8, 8], [5, 7, 3, 9], [2, 4, 3, 9], [4, 4, 4, 4]], \"output\": [[1, 3, 5, 6], [(...TRUNCATED) | [{"input": [[6, 1, 8], [1, 1, 4], [1, 6, 2]], "output": [[2, 2, 7], [7, 2, 2], [3, 1, 9]]}] | barc_heavy | ```
2 2 7
7 2 2
3 1 9
``` | 548 | "Hint: First isolate each connected same‐color region in the input. In the output you’ll find th(...TRUNCATED) | 9 | 0 | 0 | [
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to understand the transformation rule from the examples. The hint says: \"First isol(...TRUNCATED) | ["Hint: First isolate each connected same‐color region in the input. In the output you’ll find t(...TRUNCATED) | "[{\"input\": [[7, 7, 8, 8], [5, 7, 3, 9], [2, 4, 3, 9], [4, 4, 4, 4]], \"output\": [[1, 3, 5, 6], [(...TRUNCATED) | [{"input": [[6, 1, 8], [1, 1, 4], [1, 6, 2]], "output": [[2, 2, 7], [7, 2, 2], [3, 1, 9]]}] | barc_heavy | ```
2 2 7
7 2 2
3 1 9
``` | 548 | "Hint: First isolate each connected‐color region in the input. In the output you’ll find the ver(...TRUNCATED) | 9 | 0 | 0 | [
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples. There are three examples gi(...TRUNCATED) | ["Hint: First isolate each connected same‐color region in the input. In the output you’ll find t(...TRUNCATED) | "[{\"input\": [[7, 7, 8, 8], [5, 7, 3, 9], [2, 4, 3, 9], [4, 4, 4, 4]], \"output\": [[1, 3, 5, 6], [(...TRUNCATED) | [{"input": [[6, 1, 8], [1, 1, 4], [1, 6, 2]], "output": [[2, 2, 7], [7, 2, 2], [3, 1, 9]]}] | barc_heavy | ```
2 2 7
7 2 2
3 1 9
``` | 548 | "Think about the input not as a sea of numbers but as a handful of standalone shapes. In each examp(...TRUNCATED) | 9 | 0 | 0 | [
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to understand the transformation rule from the examples. The problem says that the t(...TRUNCATED) | ["Hint: First isolate each connected same‐color region in the input. In the output you’ll find t(...TRUNCATED) | "[{\"input\": [[7, 7, 8, 8], [5, 7, 3, 9], [2, 4, 3, 9], [4, 4, 4, 4]], \"output\": [[1, 3, 5, 6], [(...TRUNCATED) | [{"input": [[6, 1, 8], [1, 1, 4], [1, 6, 2]], "output": [[2, 2, 7], [7, 2, 2], [3, 1, 9]]}] | barc_heavy | ```
2 2 7
7 2 2
3 1 9
``` | 548 | "Think of this as a two‐step process: first “turn” the input 90° (so output cells line up wit(...TRUNCATED) | 9 | 0 | 0 | [
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
"<|im_start|>user\nYou will be given some number of paired example inputs and outputs grids. The out(...TRUNCATED) | ["First, I need to figure out the transformation rule from the examples to apply to the test input. (...TRUNCATED) | ["Hint: First isolate each connected same‐color region in the input. In the output you’ll find t(...TRUNCATED) | "[{\"input\": [[7, 7, 8, 8], [5, 7, 3, 9], [2, 4, 3, 9], [4, 4, 4, 4]], \"output\": [[1, 3, 5, 6], [(...TRUNCATED) | [{"input": [[6, 1, 8], [1, 1, 4], [1, 6, 2]], "output": [[2, 2, 7], [7, 2, 2], [3, 1, 9]]}] | barc_heavy | ```
2 2 7
7 2 2
3 1 9
``` | 548 | null | 9 | 0 | 0 | [
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9,
9
] | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | [
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
] |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 11