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
list
internal_answers_is_correct_per_gen
list
internal_answers_judgement_reasoning_per_gen
list
internal_answers_judgement_llm_prompt_per_gen
list
responses_to_evaluate
list
eval_extracted_answers
list
answer_is_corrects
list
answer_reasons
list
mock_budget_force_convo
dict
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...
157
{"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 [55, 60, 36, 6], create an equation that equals 157. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Show your wor...
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
[{"budget_forced_chunks": ["<think>\nTo solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the target number 157. Let's break it down:\n\nStep 1: We can start by multiplying 60 and 6, which gives us 360.\nStep 2: Now, we need to add 55 to the result ...
countdown
<think> To solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the target number 157. Let's break it down: Step 1: We can start by multiplying 60 and 6, which gives us 360. Step 2: Now, we need to add 55 to the result from Step 1. Step 3: Finally, we...
0
0
Step 1: 60 * 6 = 360 Step 2: 360 + 55 = 415 Step 3: 415 - 36 = 379
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 [55, 60, 36, 6], create an equation that equals 157. You ca...
0
false
Incorrect final answer
[ [ "Step 1: 60 * 6 = 360\nStep 2: 360 + 55 = 415\nStep 3: 415 - 36 = 379", "Step 1: 60 * 6 = 360\nStep 2: 360 + 55 = 415\nStep 3: 415 - 36 = 379", "6*60 + 55" ], [ "" ] ]
[ [ false, false, false ], [ false ] ]
[ [ "Incorrect final answer", "Incorrect final answer", "Expected a single '=' separating expression and result" ], [ "No answer" ] ]
[ [ "", "", "" ], [ "" ] ]
[ "<think>\nTo solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the target number 157. Let's break it down:\n\nStep 1: We can start by multiplying 60 and 6, which gives us 360.\nStep 2: Now, we need to add 55 to the result from Step 1.\nStep 3: F...
[ "6*60 + 55", "" ]
[ false, false ]
[ "Expected a single '=' separating expression and result", "No answer" ]
{ "content": [ "Initial Response\n\nEval Type: countdown\nExtracted Answer: 6*60 + 55\nWas Correct: False\n\nTarget: 157", "<think>\nTo solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the target number 157. Let's break it down:\n\nStep 1...
1
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
109
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem, we need to use the numbers [83, 41, (...TRUNCATED)
countdown
"<think>\nTo solve the problem, we need to use the numbers [83, 41, 3, 18] and the arithmetic operat(...TRUNCATED)
1
0
Step 1: 83 + 41 = 124 Step 2: 124 - 3 = 121 Step 3: 121 - 18 = 103 Step 4: 103 + 18 = 121
"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 4: 103 + 18 = 121
[["Step 1: 83 + 41 = 124\nStep 2: 124 - 3 = 121\nStep 3: 121 - 18 = 103\nStep 4: 103 + 18 = 121","St(...TRUNCATED)
[[false,false,false,false,false],[false,false,false],[false,false,false,false,false,false,false,fals(...TRUNCATED)
[["Line uses unavailable numbers: Step 4: 103 + 18 = 121","Line uses unavailable numbers: Step 4: 10(...TRUNCATED)
[["","","","",""],["","",""],["","","","","","","","","","","","","","","","","","","","","","","","(...TRUNCATED)
["<think>\nTo solve the problem, we need to use the numbers [83, 41, 3, 18] and the arithmetic opera(...TRUNCATED)
[ "41 + 83 - 3", "83 + 41 - 3", "83 + 41 - 3" ]
[ false, false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 41 + 83 - 3\nWas Correct: F(...TRUNCATED)
2
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
204
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [28, 100(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [28, 100, 30, 46] and the operations (+,(...TRUNCATED)
2
0
"Step 1: 28 * 100 = 2800\nStep 2: 2800 - 76 = 2724\nStep 3: 2724 / 30 = 90.8\nStep 4: 90.8 rounded d(...TRUNCATED)
"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: 2800 - 76 = 2724
[["Step 1: 28 * 100 = 2800\nStep 2: 2800 - 76 = 2724\nStep 3: 2724 / 30 = 90.8\nStep 4: 90.8 rounded(...TRUNCATED)
[ [ false, true, false ], [ false, false, false ] ]
[["Line uses unavailable numbers: Step 2: 2800 - 76 = 2724","","Expected a single '=' separating exp(...TRUNCATED)
[ [ "", "", "" ], [ "", "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [28, 100, 30, 46] and the operations (+(...TRUNCATED)
[ "46 + 100 + 30", "46 + 100 + 28" ]
[ false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 46 + 100 + 30\nWas Correct:(...TRUNCATED)
3
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
837
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to find an equation using t(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to find an equation using the numbers [77, 22, 93, 46] with(...TRUNCATED)
3
0
Step 1: 77 * 22 = 1694 Step 2: 1694 + 93 = 1787 Step 3: 1787 - 46 = 1741
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Incorrect final answer
[["Step 1: 77 * 22 = 1694\nStep 2: 1694 + 93 = 1787\nStep 3: 1787 - 46 = 1741","Step 1: 77 + 22 = 99(...TRUNCATED)
[ [ false, false, false, false, false, false, false, false, false ] ]
[["Incorrect final answer","Incorrect final answer","Incorrect final answer","Incorrect final answer(...TRUNCATED)
[ [ "", "", "", "", "", "", "", "", "" ] ]
["<think>\nTo solve this problem, we need to find an equation using the numbers [77, 22, 93, 46] wit(...TRUNCATED)
[ "Step 1: 77 + 22 = 99\nStep 2: 99 + 93 = 192\nStep 3: 192 + 46 = 238" ]
[ false ]
[ "Incorrect final answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 77 + 22 = 99\nStep (...TRUNCATED)
4
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
224
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to find a combination of th(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to find a combination of the given numbers [31, 44, 21, 28](...TRUNCATED)
4
0
Step 1: 44 * 28 = 1256 Step 2: 1256 + 31 = 1287 Step 3: 1287 + 21 = 224
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Incorrect arithmetic in line: Step 1: 44 * 28 = 1256
[["Step 1: 44 * 28 = 1256\nStep 2: 1256 + 31 = 1287\nStep 3: 1287 + 21 = 224","Step 1: 44 + 28 = 72\(...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED)
[["Incorrect arithmetic in line: Step 1: 44 * 28 = 1256","Incorrect final answer","Incorrect final a(...TRUNCATED)
[["","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""(...TRUNCATED)
["<think>\nTo solve this problem, we need to find a combination of the given numbers [31, 44, 21, 28(...TRUNCATED)
[ "Step 1: 44 + 28 = 72\nStep 2: 72 * 31 = 2232\nStep 3: 2232 - 21 = 2211" ]
[ false ]
[ "Incorrect final answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 44 + 28 = 72\nStep (...TRUNCATED)
5
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
358
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the given numbers [4(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the given numbers [44, 5, 80, 58] and apply basic ar(...TRUNCATED)
5
0
Step 1: 44 * 5 = 220 Step 2: 220 + 80 = 300 Step 3: 300 / 2 = 150
"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: 300 / 2 = 150
[["Step 1: 44 * 5 = 220\nStep 2: 220 + 80 = 300\nStep 3: 300 / 2 = 150","Step 1: 44 * 5 = 220\nStep (...TRUNCATED)
[[false,true,false],[false,false],[false,false,false,false,false,false,false,false,false,false,false(...TRUNCATED)
[["Line uses unavailable numbers: Step 3: 300 / 2 = 150","","Expected a single '=' separating expres(...TRUNCATED)
[["","",""],["",""],["","","","","","","","","","","","","","","","","","","","","","","","","","","(...TRUNCATED)
["<think>\nTo solve this problem, we need to use the given numbers [44, 5, 80, 58] and apply basic a(...TRUNCATED)
[ "44*5 + 80", "44*5 + 80", "44*5 + 80 + 58" ]
[ false, false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 44*5 + 80\nWas Correct: Fal(...TRUNCATED)
6
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
110
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
1
[true]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem using the numbers [81, 29, 95, 37] an(...TRUNCATED)
countdown
"<think>\nTo solve the problem using the numbers [81, 29, 95, 37] and the operations (+, -, *, /), w(...TRUNCATED)
6
0
"Step 1: 81 + 95 = 176\nStep 2: 176 - 37 = 139\nStep 3: 139 + 29 = 168\nStep 4: 168 - 95 = 73\nStep (...TRUNCATED)
"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 4: 168 - 95 = 73
[["Step 1: 81 + 95 = 176\nStep 2: 176 - 37 = 139\nStep 3: 139 + 29 = 168\nStep 4: 168 - 95 = 73\nSte(...TRUNCATED)
[[false,true,false],[false,true,false],[true,false,true,false,true,false,false,false],[true,false,tr(...TRUNCATED)
[["Line uses unavailable numbers: Step 4: 168 - 95 = 73","","Expected a single '=' separating expres(...TRUNCATED)
[ [ "", "", "" ], [ "", "", "" ], [ "", "", "", "", "", "", "", "" ], [ "", "", "" ] ]
["<think>\nTo solve the problem using the numbers [81, 29, 95, 37] and the operations (+, -, *, /), (...TRUNCATED)
[ "29 + 81 + 95 + 37", "29 + 81 + 95 + 37", "29 + 81 + 95", "Step 1: 81 + 29 = 110" ]
[ false, false, false, true ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 29 + 81 + 95 + 37\nWas Corr(...TRUNCATED)
7
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
896
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [65, 56,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [65, 56, 37, 12] and the operations (+, (...TRUNCATED)
7
0
Step 1: 65 * 56 = 3640 Step 2: 3640 + 37 = 3677 Step 3: 3677 - 12 = 896
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Incorrect arithmetic in line: Step 3: 3677 - 12 = 896
[["Step 1: 65 * 56 = 3640\nStep 2: 3640 + 37 = 3677\nStep 3: 3677 - 12 = 896","Step 1: 65 * 37 = 235(...TRUNCATED)
[ [ false, false, false ], [ false, false, false, false, false, false ], [ false ] ]
[["Incorrect arithmetic in line: Step 3: 3677 - 12 = 896","Incorrect arithmetic in line: Step 1: 65 (...TRUNCATED)
[ [ "", "", "" ], [ "", "", "", "", "", "" ], [ "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [65, 56, 37, 12] and the operations (+,(...TRUNCATED)
[ "65*37 + 56", "65*37 + 56", "" ]
[ false, false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 65*37 + 56\nWas Correct: Fa(...TRUNCATED)
8
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
189
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem using the numbers [4, 13, 64, 60], we(...TRUNCATED)
countdown
"<think>\nTo solve the problem using the numbers [4, 13, 64, 60], we need to find an equation that e(...TRUNCATED)
8
0
Step 1: 13 * 6 = 78 Step 2: 78 + 11 = 89 Step 3: 89 - 10 = 79
"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 1: 13 * 6 = 78
[["Step 1: 13 * 6 = 78\nStep 2: 78 + 11 = 89\nStep 3: 89 - 10 = 79","(13 * 6) + 4 = 189","13*6 + 4"](...TRUNCATED)
[[false,false,false],[false,false],[false,false,false,false,false,false,false,false,false,false,fals(...TRUNCATED)
[["Line uses unavailable numbers: Step 1: 13 * 6 = 78","Expression does not equal stated result","Ex(...TRUNCATED)
[["","",""],["",""],["","","","","","","","","","","","","","","","","","","","","","","","","","","(...TRUNCATED)
["<think>\nTo solve the problem using the numbers [4, 13, 64, 60], we need to find an equation that (...TRUNCATED)
[ "13*6 + 4", "60 + 13 * 4", "60 + 4*13" ]
[ false, false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 13*6 + 4\nWas Correct: Fals(...TRUNCATED)
9
"{\"prompt\": [{\"content\": \"Solve the problem step by step. Think step by step first.\\nThe answe(...TRUNCATED)
298
"{\"gen_args_0\": {\"arg_0\": \"<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are(...TRUNCATED)
0
[false]
samples_countdown4arg_2025-07-08T07-19-35.811120.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the given numbers [6(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the given numbers [62, 56, 32, 55] exactly once and (...TRUNCATED)
9
0
62 * 55 - 56 - 32 - 50 - 42 - 32 - 16 - 8 - 0 = 298
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Expression does not equal stated result
[["62 * 55 - 56 - 32 - 50 - 42 - 32 - 16 - 8 - 0 = 298","62 + 55 - 56 - 32 - 50 - 42 - 32 - 16 - 8 -(...TRUNCATED)
[[false,false,false],[false],[false,false,false,false,false],[false,false,false,false,false,false,fa(...TRUNCATED)
[["Expression does not equal stated result","Expression does not equal stated result","Expected a si(...TRUNCATED)
[["","",""],[""],["","","","",""],["","","","","","","","","","","","","","","","","","","","","",""(...TRUNCATED)
["<think>\nTo solve this problem, we need to use the given numbers [62, 56, 32, 55] exactly once and(...TRUNCATED)
["62 + 55 - 56 - 32 - 50 - 42 - 32 - 16 - 8 - 0","62 + 55 - 56 - 32 - 50 - 42 - 32 - 16 - 8 - 0","62(...TRUNCATED)
[ false, false, false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 62 + 55 - 56 - 32 - 50 - 42(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
4