Dataset Viewer
Auto-converted to Parquet Duplicate
doc_id
int64
doc
string
target
string
arguments
string
exact_match
int64
extracted_answers
string
source_file
string
info
string
eval_type
string
response_to_evaluate
string
row_idx
int64
gen_idx
int64
eval_extracted_answer
string
answer_extraction_llm_prompt
string
answer_extraction_reasoning
string
answer_idx
int64
answer_is_correct
bool
answer_judgement_reasoning
string
answer_judgement_llm_prompt
string
internal_answers_per_gen
sequence
internal_answers_is_correct_per_gen
sequence
internal_answers_judgement_reasoning_per_gen
sequence
internal_answers_judgement_llm_prompt_per_gen
sequence
responses_to_evaluate
sequence
eval_extracted_answers
sequence
answer_is_corrects
sequence
mock_budget_force_convo
list
0
{"prompt": [{"content": "Solve the problem step by step. Think step by step first.\nThe answer is a series of arithmetic operations (+, -, *, /) that results in the target number.\n\nWrite the final answer in <answer> </answer> tags.\nFor the final answer, make sure that each step in the final answer is written as Step...
125
{"gen_args_0": {"arg_0": "<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\nUsing the numbers [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Show your work b...
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
[{"budget_forced_chunks": ["To solve the problem of creating an equation using the numbers [96, 97, 68] that equals 125, we need to use basic arithmetic operations. Here's the step-by-step process:\n\n1. Start by adding 96 and 97:\n 96 + 97 = 193\n\n2. Now, we need to adjust this result to get closer to 125. We can s...
countdown
To solve the problem of creating an equation using the numbers [96, 97, 68] that equals 125, we need to use basic arithmetic operations. Here's the step-by-step process: 1. Start by adding 96 and 97: 96 + 97 = 193 2. Now, we need to adjust this result to get closer to 125. We can subtract 68 from 193: 193 - 68 ...
0
0
Step 1: 96 + 97 = 193 Step 2: 193 - 68 = 125
Given the prompt and the response from the langauge model, extract the answer given by the model for the question. # Question <|im_start|>system You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|> <|im_start|>user Using the numbers [96, 97, 68], create an equation that equals 125. You can u...
0
true
[ [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ], [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ], [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ], [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ], [ "Step 1: 96 +...
[ [ true ], [ true ], [ true ], [ true, true ], [ true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, ...
[ [ "" ], [ "" ], [ "" ], [ "", "" ], [ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ...
[ [ "" ], [ "" ], [ "" ], [ "", "" ], [ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ...
[ "To solve the problem of creating an equation using the numbers [96, 97, 68] that equals 125, we need to use basic arithmetic operations. Here's the step-by-step process:\n\n1. Start by adding 96 and 97:\n 96 + 97 = 193\n\n2. Now, we need to adjust this result to get closer to 125. We can subtract 68 from 193:\n ...
[ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ]
[ true, true, true, true, true ]
[ { "content": "Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125\nWas Correct: True\nTarget: 125", "role": "user" }, { "content": "To solve the problem of creating an equation using the numbers [96, 97, 68] that equals 125, we need to use basic ...
1
{"prompt": [{"content": "Solve the problem step by step. Think step by step first.\nThe answer is a series of arithmetic operations (+, -, *, /) that results in the target number.\n\nWrite the final answer in <answer> </answer> tags.\nFor the final answer, make sure that each step in the final answer is written as Step...
105
{"gen_args_0": {"arg_0": "<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\nUsing the numbers [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Show your work b...
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
[{"budget_forced_chunks": ["To solve this problem, we need to use the numbers [21, 80, 46] and the operations (+, -, *, /) to reach the target number 105. Let's break it down:\n\nStep 1: We need to start with the number 21. Let's try to use it in a way that will help us reach 105.\n\nStep 2: We can start by adding 80 t...
countdown
To solve this problem, we need to use the numbers [21, 80, 46] and the operations (+, -, *, /) to reach the target number 105. Let's break it down: Step 1: We need to start with the number 21. Let's try to use it in a way that will help us reach 105. Step 2: We can start by adding 80 to 21, which gives us 101. Now we...
1
0
Given the prompt and the response from the langauge model, extract the answer given by the model for the question. # Question <|im_start|>system You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|> <|im_start|>user Using the numbers [21, 80, 46], create an equation that equals 105. You can u...
0
false
No answer
[ [ "" ] ]
[ [ false ] ]
[ [ "No answer" ] ]
[ [ "" ] ]
[ "To solve this problem, we need to use the numbers [21, 80, 46] and the operations (+, -, *, /) to reach the target number 105. Let's break it down:\n\nStep 1: We need to start with the number 21. Let's try to use it in a way that will help us reach 105.\n\nStep 2: We can start by adding 80 to 21, which gives us 10...
[ "" ]
[ false ]
[ { "content": "Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\nTarget: 105", "role": "user" }, { "content": "To solve this problem, we need to use the numbers [21, 80, 46] and the operations (+, -, *, /) to reach the target number 105. Let's break it down:\n\nStep 1:...
2
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
500
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [6, 76, 96] and ap(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [6, 76, 96] and apply basic arithmetic operations(...TRUNCATED)
2
0
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
No answer
[ [ "" ] ]
[ [ false ] ]
[ [ "No answer" ] ]
[ [ "" ] ]
["To solve this problem, we need to use the numbers [6, 76, 96] and apply basic arithmetic operation(...TRUNCATED)
[ "" ]
[ false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\nTarge(...TRUNCATED)
3
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
630
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [42, 12, 3] and ap(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [42, 12, 3] and apply basic arithmetic operations(...TRUNCATED)
3
0
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
No answer
[ [ "" ] ]
[ [ false ] ]
[ [ "No answer" ] ]
[ [ "" ] ]
["To solve this problem, we need to use the numbers [42, 12, 3] and apply basic arithmetic operation(...TRUNCATED)
[ "" ]
[ false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\nTarge(...TRUNCATED)
4
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
194
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
1
[true]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [18, 85, 91] and t(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [18, 85, 91] and the arithmetic operations (+, -,(...TRUNCATED)
4
0
Step 1: 91 + 18 = 109 Step 2: 109 + 85 = 194
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 91 + 18 = 109\nStep 2: 109 + 85 = 194"],[""],["Step 1: 91 + 18 = 109\nStep 2: 109 + 85 = (...TRUNCATED)
[[true],[false],[true],[false],[true],[true,true,true,true,true,true,true,true,true,true,true,true,t(...TRUNCATED)
[[""],["No answer"],[""],["No answer"],[""],["","","","","","","","","","","","","","","","","","","(...TRUNCATED)
[[""],[""],[""],[""],[""],["","","","","","","","","","","","","","","","","","","","","","","","","(...TRUNCATED)
["To solve this problem, we need to use the numbers [18, 85, 91] and the arithmetic operations (+, -(...TRUNCATED)
["Step 1: 91 + 18 = 109\nStep 2: 109 + 85 = 194","","Step 1: 91 + 18 = 109\nStep 2: 109 + 85 = 194",(...TRUNCATED)
[ true, false, true, false, true, true ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 91 + 18 = 109\nStep(...TRUNCATED)
5
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
103
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [86, 69, 52] and t(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [86, 69, 52] and the operations (+, -, *, /) to r(...TRUNCATED)
5
0
Step 1: 86 - 52 = 34 Step 2: 34 + 69 = 103
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 86 - 52 = 34\nStep 2: 34 + 69 = 103"],["Step 1: 86 - 52 = 34\nStep 2: 34 + 69 = 103"],["S(...TRUNCATED)
[[true],[true],[true],[true],[true,true,true,true,true,true,true,true,true,true,true,true,true,true,(...TRUNCATED)
[[""],[""],[""],[""],["","","","","","","","","","","","","","","","","","","","","","","","","","",(...TRUNCATED)
[[""],[""],[""],[""],["","","","","","","","","","","","","","","","","","","","","","","","","","",(...TRUNCATED)
["To solve this problem, we need to use the numbers [86, 69, 52] and the operations (+, -, *, /) to (...TRUNCATED)
["Step 1: 86 - 52 = 34\nStep 2: 34 + 69 = 103","Step 1: 86 - 52 = 34\nStep 2: 34 + 69 = 103","Step 1(...TRUNCATED)
[ true, true, true, true, true ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 86 - 52 = 34\nStep (...TRUNCATED)
6
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
354
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve the problem of creating an equation using the numbers [63, (...TRUNCATED)
countdown
"To solve the problem of creating an equation using the numbers [63, 7, 87] that equals 354, we need(...TRUNCATED)
6
0
Step 1: 63 + 7 = 70 Step 2: 87 + 70 = 157 Step 3: 157 + 197 = 354
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Line uses unavailable numbers: Step 3: 157 + 197 = 354
[["Step 1: 63 + 7 = 70\nStep 2: 87 + 70 = 157\nStep 3: 157 + 197 = 354"],["Step 1: 63 + 7 = 70\nStep(...TRUNCATED)
[ [ false ], [ false ], [ false ], [ false ], [ false ], [ false ] ]
[["Line uses unavailable numbers: Step 3: 157 + 197 = 354"],["Line uses unavailable numbers: Step 3:(...TRUNCATED)
[ [ "" ], [ "" ], [ "" ], [ "" ], [ "" ], [ "" ] ]
["To solve the problem of creating an equation using the numbers [63, 7, 87] that equals 354, we nee(...TRUNCATED)
["Step 1: 63 + 7 = 70\nStep 2: 87 + 70 = 157\nStep 3: 157 + 197 = 354","Step 1: 63 + 7 = 70\nStep 2:(...TRUNCATED)
[ false, false, false, false, false, false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 63 + 7 = 70\nStep 2(...TRUNCATED)
7
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
102
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [8, 50, 19] and th(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [8, 50, 19] and the operations (+, -, *, /) to re(...TRUNCATED)
7
0
Step 1: 8 + 50 = 58 Step 2: 58 + 44 = 102
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Line uses unavailable numbers: Step 2: 58 + 44 = 102
[["Step 1: 8 + 50 = 58\nStep 2: 58 + 44 = 102"],["Step 1: 50 + 19 = 69\nStep 2: 69 + 8 = 77\nStep 3:(...TRUNCATED)
[ [ false ], [ false ], [ false ] ]
[["Line uses unavailable numbers: Step 2: 58 + 44 = 102"],["Line uses unavailable numbers: Step 3: 7(...TRUNCATED)
[ [ "" ], [ "" ], [ "" ] ]
["To solve this problem, we need to use the numbers [8, 50, 19] and the operations (+, -, *, /) to r(...TRUNCATED)
["Step 1: 8 + 50 = 58\nStep 2: 58 + 44 = 102","Step 1: 50 + 19 = 69\nStep 2: 69 + 8 = 77\nStep 3: 77(...TRUNCATED)
[ false, false, false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 8 + 50 = 58\nStep 2(...TRUNCATED)
8
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
124
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [38, 46, 40] and t(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [38, 46, 40] and the operations (+, -, *, /) to r(...TRUNCATED)
8
0
Step 1: 38 + 46 = 84 Step 2: 84 + 40 = 124
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124"],["Step 1: 38 + 46 = 84\nStep 2: 84 = 124"],["Step 1(...TRUNCATED)
[[true],[false],[true,true,false,false,false,false,false],[false,false,false,false,false,false,false(...TRUNCATED)
[[""],["Incorrect arithmetic in line: Step 2: 84 = 124"],["","","Line uses unavailable numbers: Step(...TRUNCATED)
[[""],[""],["","","","","","",""],["","","","","","","","","","","","","","","","","","","","","",""(...TRUNCATED)
["To solve this problem, we need to use the numbers [38, 46, 40] and the operations (+, -, *, /) to (...TRUNCATED)
["Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124","Step 1: 38 + 46 = 84\nStep 2: 84 = 124","Step 1: 46 (...TRUNCATED)
[ true, false, false, false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 38 + 46 = 84\nStep (...TRUNCATED)
9
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
132
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
1
[true]
samples_countdown_2025-06-15T16-38-59.818527.jsonl
"[{\"budget_forced_chunks\": [\"To solve this problem, we need to use the numbers [92, 21, 19] and a(...TRUNCATED)
countdown
"To solve this problem, we need to use the numbers [92, 21, 19] and apply basic arithmetic operation(...TRUNCATED)
9
0
Step 1: 92 + 21 = 113 Step 2: 113 + 19 = 132
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[ [ "Step 1: 92 + 21 = 113\nStep 2: 113 + 19 = 132" ], [ "" ], [ "" ], [ "" ] ]
[ [ true ], [ false ], [ false ], [ false ] ]
[ [ "" ], [ "No answer" ], [ "No answer" ], [ "No answer" ] ]
[ [ "" ], [ "" ], [ "" ], [ "" ] ]
["To solve this problem, we need to use the numbers [92, 21, 19] and apply basic arithmetic operatio(...TRUNCATED)
[ "Step 1: 92 + 21 = 113\nStep 2: 113 + 19 = 132", "", "", "" ]
[ true, false, false, false ]
[{"content":"Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 92 + 21 = 113\nStep(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
2