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_2025-07-09T01-34-37.214121.jsonl
[{"budget_forced_chunks": ["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and seeing which agree the most. The one that agrees the most is probably right.\n\n<attempt>\nTo solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations ...
countdown
<think> To answer this, I will try answering it multiple times, then checking those answers and seeing which agree the most. The one that agrees the most is probably right. <attempt> To solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the target n...
0
0
36 + 60 + 55
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
Expected a single '=' separating expression and result
[ [ "36 + 60 + 55" ], [ "36 + 60 + 55", "60 + 55 + 36", "36 + 60 + 55", "60 + 55 + 36" ], [ "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36", "60 + 55 + 36"...
[ [ false ], [ false, false, false, false ], [ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, ...
[ [ "Expected a single '=' separating expression and result" ], [ "Expected a single '=' separating expression and result", "Expected a single '=' separating expression and result", "Expected a single '=' separating expression and result", "Expected a single '=' separating expression and resul...
[ [ "" ], [ "", "", "", "" ], [ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ...
[ "<think>\nTo answer this, I will try answering it multiple times, then checking those answers and seeing which agree the most. The one that agrees the most is probably right.\n\n<attempt>\nTo solve this problem, we need to use the numbers [55, 60, 36, 6] and apply basic arithmetic operations (+, -, *, /) to get the...
[ "36 + 60 + 55", "60 + 55 + 36", "60 + 55 + 36" ]
[ false, false, false ]
[ "Expected a single '=' separating expression and result", "Expected a single '=' separating expression and result", "Expected a single '=' separating expression and result" ]
{ "content": [ "Initial Response\n\nEval Type: countdown\nExtracted Answer: 36 + 60 + 55\nWas Correct: False\n\nTarget: 157", "<think>\nTo answer this, I will try answering it multiple times, then checking those answers and seeing which agree the most. The one that agrees the most is probably right.\n\n<attem...
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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
1
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" ] ]
[ [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
2
0
46*4 + 20
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Expected a single '=' separating expression and result
[["46*4 + 20"],["28*30 - 46","28*30 - 46","28*30 - 46","28*30 - 46","28*30 - 46","28*30 - 46","28*30(...TRUNCATED)
[ [ false ], [ false, false, false, false, false, false, false, false ] ]
[["Expected a single '=' separating expression and result"],["Expected a single '=' separating expre(...TRUNCATED)
[ [ "" ], [ "", "", "", "", "", "", "", "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "46*4 + 20", "28*30 - 46" ]
[ 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*4 + 20\nWas Correct: Fal(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...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" ] ]
[ [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
4
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" ] ]
[ [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
5
0
44*5 + 80 + 58
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Expected a single '=' separating expression and result
[["44*5 + 80 + 58"],["44*5 + 80 + 58"],["44*5 + 80 + 58","44*5 + 80 + 58","44*5 + 80 + 58","44*5 + 8(...TRUNCATED)
[[false],[false],[false,false,false,false,false,false,false,false,false,false,false,false,false,fals(...TRUNCATED)
[["Expected a single '=' separating expression and result"],["Expected a single '=' separating expre(...TRUNCATED)
[[""],[""],["","","","","","","","","","","","","","","","","","","","","","","","","","","","","","(...TRUNCATED)
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "44*5 + 80 + 58", "44*5 + 80 + 58", "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 + 58\nWas Correct(...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)
0
[false]
samples_countdown4arg_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
6
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" ] ]
[ [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
7
0
65*12 + 56 + 37
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Expected a single '=' separating expression and result
[ [ "65*12 + 56 + 37" ], [ "65*12 + 56 + 37" ], [ "" ] ]
[ [ false ], [ false ], [ false ] ]
[["Expected a single '=' separating expression and result"],["Expected a single '=' separating expre(...TRUNCATED)
[ [ "" ], [ "" ], [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "65*12 + 56 + 37", "65*12 + 56 + 37", "" ]
[ 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*12 + 56 + 37\nWas Correc(...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
8
0
60*64/4 + 13
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
false
Expected a single '=' separating expression and result
[ [ "60*64/4 + 13" ], [ "" ] ]
[ [ false ], [ false ] ]
[ [ "Expected a single '=' separating expression and result" ], [ "No answer" ] ]
[ [ "" ], [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "60*64/4 + 13", "" ]
[ false, false ]
[ "Expected a single '=' separating expression and result", "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 60*64/4 + 13\nWas Correct: (...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_2025-07-09T01-34-37.214121.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo answer this, I will try answering it multiple times, th(...TRUNCATED)
countdown
"<think>\nTo answer this, I will try answering it multiple times, then checking those answers and se(...TRUNCATED)
9
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" ] ]
[ [ "" ] ]
["<think>\nTo answer this, I will try answering it multiple times, then checking those answers and s(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
2