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_2025-07-09T01-15-02.268926.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.\n\nHere's one possible solution:\n\nStep 1: Start with 55 and add 60 \n55 + 60 = 115\n\nStep 2: Subtract 36 from the result of step 1\n1...
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. Here's one possible solution: Step 1: Start with 55 and add 60 55 + 60 = 115 Step 2: Subtract 36 from the result of step 1 115 - 36 = 79 Wait... this is wrong, ...
0
0
Step 1: 55 + 60 = 115 Step 2: 115 + 36 = 151 Step 3: 151 + 6 = 157
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
true
[ [ "Step 1: 55 + 60 = 115\nStep 2: 115 + 36 = 151\nStep 3: 151 + 6 = 157", "Step 1: 55 + 60 = 115\nStep 2: 115 + 36 = 151\nStep 3: 151 + 6 = 157", "Step 1: 60 + 36 = 96\nStep 2: 55 + 96 = 151\nStep 3: 151 + 6 = 157", "Step 1: 55 + 60 = 115\nStep 2: 115 - 36 = 79" ] ]
[ [ true, true, true, false ] ]
[ [ "", "", "", "Incorrect final 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.\n\nHere's one possible solution:\n\nStep 1: Start with 55 and add 60 \n55 + 60 = 115\n\nStep 2: Subtract 36 from the result of step 1\n115 - 36 = 79\n\nWait......
[ "Step 1: 55 + 60 = 115\nStep 2: 115 - 36 = 79" ]
[ false ]
[ "Incorrect final answer" ]
{ "content": [ "Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 55 + 60 = 115\nStep 2: 115 - 36 = 79\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 ...
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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [83, 41,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [83, 41, 3, 18] and apply basic arithmet(...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
[["","Step 1: 83 + 41 = 124\nStep 2: 124 + 3 = 127\nStep 3: 127 - 18 = 109","Step 1: 83 + 41 = 124\n(...TRUNCATED)
[ [ false, true, true ], [ true, true, true, false, false, true, false, false, false ] ]
[["No answer","",""],["","","","Incorrect final answer","No answer","","Incorrect final answer","Inc(...TRUNCATED)
[ [ "", "", "" ], [ "", "", "", "", "", "", "", "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [83, 41, 3, 18] and apply basic arithme(...TRUNCATED)
[ "Step 1: 83 + 41 = 124\nStep 2: 124 + 3 = 127\nStep 3: 127 - 18 = 109", "" ]
[ true, false ]
[ "", "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 83 + 41 = 124\nStep(...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)
1
[true]
samples_countdown4arg_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem of creating an equation using the num(...TRUNCATED)
countdown
"<think>\nTo solve the problem of creating an equation using the numbers [28, 100, 30, 46] that equa(...TRUNCATED)
2
0
Step 1: 100 + 46 = 146 Step 2: 146 + 28 = 174 Step 3: 174 + 30 = 204
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 100 + 46 = 146\nStep 2: 146 + 28 = 174\nStep 3: 174 + 30 = 204","Step 1: 100 + 46 = 146\n(...TRUNCATED)
[ [ true, true ], [ false ] ]
[ [ "", "" ], [ "No answer" ] ]
[ [ "", "" ], [ "" ] ]
["<think>\nTo solve the problem of creating an equation using the numbers [28, 100, 30, 46] that equ(...TRUNCATED)
[ "Step 1: 100 + 46 = 146\nStep 2: 146 + 28 = 174\nStep 3: 174 + 30 = 204", "" ]
[ true, false ]
[ "", "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 100 + 46 = 146\nSte(...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [77, 22,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [77, 22, 93, 46] and the 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" ] ]
[ [ "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [77, 22, 93, 46] and the operations (+,(...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [31, 44,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [31, 44, 21, 28] and the operations (+, (...TRUNCATED)
4
0
Step 1: 44 - 21 = 23 Step 2: 23 + 28 = 51 Step 3: 51 * 4 = 204 Step 4: 204 + 28 = 232
"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: 51 * 4 = 204
[["Step 1: 44 - 21 = 23\nStep 2: 23 + 28 = 51\nStep 3: 51 * 4 = 204\nStep 4: 204 + 28 = 232","Step 1(...TRUNCATED)
[ [ false, false ] ]
[["Line uses unavailable numbers: Step 3: 51 * 4 = 204","Incorrect arithmetic in line: Step 2: 1232 (...TRUNCATED)
[ [ "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [31, 44, 21, 28] and the operations (+,(...TRUNCATED)
["Step 1: 28 * 44 = 1232\nStep 2: 1232 - 31 = 1191\nStep 3: 1191 - 21 = 1170\nStep 4: 1170 - 28 = 11(...TRUNCATED)
[ false ]
[ "Incorrect arithmetic in line: Step 2: 1232 - 31 = 1191" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 28 * 44 = 1232\nSte(...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)
1
[true]
samples_countdown4arg_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [44, 5, (...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [44, 5, 80, 58] and the operations (+, -(...TRUNCATED)
5
0
Step 1: 44 * 5 = 220 Step 2: 220 + 80 = 300 Step 3: 300 + 58 = 358
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 44 * 5 = 220\nStep 2: 220 + 80 = 300\nStep 3: 300 + 58 = 358","Step 1: 44 * 5 = 220\nStep(...TRUNCATED)
[ [ true, true ], [ true, true ], [ true, true ], [ true ] ]
[ [ "", "" ], [ "", "" ], [ "", "" ], [ "" ] ]
[ [ "", "" ], [ "", "" ], [ "", "" ], [ "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [44, 5, 80, 58] and the operations (+, (...TRUNCATED)
["Step 1: 44 * 5 = 220\nStep 2: 220 + 80 = 300\nStep 3: 300 + 58 = 358","Step 1: 44 * 5 = 220\nStep (...TRUNCATED)
[ true, true, true, true ]
[ "", "", "", "" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 44 * 5 = 220\nStep (...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [81, 29,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [81, 29, 95, 37] and apply basic arithme(...TRUNCATED)
6
0
Step 1: 81 + 29 = 110
"Given the prompt and the response from the langauge model, extract the answer given by the model fo(...TRUNCATED)
0
true
[["Step 1: 81 + 29 = 110","Step 1: 81 + 29 = 110","Step 1: 81 + 29 = 110"],[""],["Step 1: 81 + 29 = (...TRUNCATED)
[ [ true, true, true ], [ false ], [ true, true ], [ false, false ] ]
[["","",""],["No answer"],["",""],["Line uses unavailable numbers: Step 3: 81 + 29 = 110","Line uses(...TRUNCATED)
[ [ "", "", "" ], [ "" ], [ "", "" ], [ "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [81, 29, 95, 37] and apply basic arithm(...TRUNCATED)
["Step 1: 81 + 29 = 110","","Step 1: 81 + 29 = 110","Step 1: 81 + 29 = 110\nStep 2: 95 - 37 = 58\nSt(...TRUNCATED)
[ true, false, true, false ]
[ "", "No answer", "", "Line uses unavailable numbers: Step 3: 81 + 29 = 110" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 81 + 29 = 110\nWas (...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem of creating an equation using the num(...TRUNCATED)
countdown
"<think>\nTo solve the problem of creating an equation using the numbers [65, 56, 37, 12] that equal(...TRUNCATED)
7
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 solve the problem of creating an equation using the numbers [65, 56, 37, 12] that equa(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem of creating an equation using the num(...TRUNCATED)
countdown
"<think>\nTo solve the problem of creating an equation using the numbers [4, 13, 64, 60] that equals(...TRUNCATED)
8
0
Step 1: 64 + 13 = 77 Step 2: 77 + 4 = 81 Step 3: 81 + 60 = 189
"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: 81 + 60 = 189
[ [ "Step 1: 64 + 13 = 77\nStep 2: 77 + 4 = 81\nStep 3: 81 + 60 = 189" ] ]
[ [ false ] ]
[ [ "Incorrect arithmetic in line: Step 3: 81 + 60 = 189" ] ]
[ [ "" ] ]
["<think>\nTo solve the problem of creating an equation using the numbers [4, 13, 64, 60] that equal(...TRUNCATED)
[ "Step 1: 64 + 13 = 77\nStep 2: 77 + 4 = 81\nStep 3: 81 + 60 = 189" ]
[ false ]
[ "Incorrect arithmetic in line: Step 3: 81 + 60 = 189" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 64 + 13 = 77\nStep (...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_2025-07-09T01-15-02.268926.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem of creating an equation using the num(...TRUNCATED)
countdown
"<think>\nTo solve the problem of creating an equation using the numbers [62, 56, 32, 55] that equal(...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 solve the problem of creating an equation using the numbers [62, 56, 32, 55] that equa(...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