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...
1
[true]
samples_countdown4arg_2025-07-08T06-42-16.984912.jsonl
[{"budget_forced_chunks": ["<think>\nTo solve this problem, we need to use the numbers [55, 60, 36] and the operations (+, -, *, /) to reach the target number 157. Let's break it down:\n\n1. First, we can add 55 and 60 to get 115.\n Step 1: 55 + 60 = 115\n\n2. Now, we need to reach 157. We can do this by adding 36 to...
countdown
<think> To solve this problem, we need to use the numbers [55, 60, 36] and the operations (+, -, *, /) to reach the target number 157. Let's break it down: 1. First, we can add 55 and 60 to get 115. Step 1: 55 + 60 = 115 2. Now, we need to reach 157. We can do this by adding 36 to 115. Step 2: 115 + 36 = 157 T...
0
0
Step 1: 55 + 60 = 115 Step 2: 115 + 36 = 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
false
Incorrect arithmetic in line: Step 2: 115 + 36 = 157
[ [ "Step 1: 55 + 60 = 115\nStep 2: 115 + 36 = 157", "60 + 36 + 55" ], [ "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: 55 + 60 = 115\nStep 2: 115 + 36 = 151\nStep 3: 151 + 6 = 157", "...
[ [ false, false ], [ true, true, true, false, true ], [ true ], [ true ], [ true, false, true, false, true, true, true, true, false ], [ true, true, true, true, true, true, true, true, true...
[ [ "Incorrect arithmetic in line: Step 2: 115 + 36 = 157", "Expected a single '=' separating expression and result" ], [ "", "", "", "Expected a single '=' separating expression and result", "" ], [ "" ], [ "" ], [ "", "Expected a single '=' separating expr...
[ [ "", "" ], [ "", "", "", "", "" ], [ "" ], [ "" ], [ "", "", "", "", "", "", "", "", "" ], [ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ...
[ "<think>\nTo solve this problem, we need to use the numbers [55, 60, 36] and the operations (+, -, *, /) to reach the target number 157. Let's break it down:\n\n1. First, we can add 55 and 60 to get 115.\n Step 1: 55 + 60 = 115\n\n2. Now, we need to reach 157. We can do this by adding 36 to 115.\n Step 2: 115 +...
[ "60 + 36 + 55", "Step 1: 6 + 55 = 61\nStep 2: 61 + 36 = 97\nStep 3: 97 + 60 = 157", "Step 1: 6 + 55 = 61\nStep 2: 61 + 36 = 97\nStep 3: 97 + 60 = 157", "Step 1: 6 + 55 = 61\nStep 2: 61 + 36 = 97\nStep 3: 97 + 60 = 157", "6 + 55 + 36 + 60", "Step 1: 55 + 60 = 115\nStep 2: 115 + 36 = 151\nStep 3: 151 + 6 = ...
[ false, true, true, true, false, true ]
[ "Expected a single '=' separating expression and result", "", "", "", "Expected a single '=' separating expression and result", "" ]
{ "content": [ "Initial Response\n\nEval Type: countdown\nExtracted Answer: 60 + 36 + 55\nWas Correct: False\n\nTarget: 157", "<think>\nTo solve this problem, we need to use the numbers [55, 60, 36] and the operations (+, -, *, /) to reach the target number 157. Let's break it down:\n\n1. First, we can add 55...
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_2025-07-08T06-42-16.984912.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 the operations (+, -(...TRUNCATED)
1
0
Step 1: 83 - 41 = 42 Step 2: 42 + 3 = 45 Step 3: 45 * 2 = 90 Step 4: 90 + 18 = 109
"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: 45 * 2 = 90
[["Step 1: 83 - 41 = 42\nStep 2: 42 + 3 = 45\nStep 3: 45 * 2 = 90\nStep 4: 90 + 18 = 109","Step 1: 1(...TRUNCATED)
[ [ false, false ] ]
[["Line uses unavailable numbers: Step 3: 45 * 2 = 90","Line uses unavailable numbers: Step 2: -23 +(...TRUNCATED)
[ [ "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [83, 41, 3, 18] and the operations (+, (...TRUNCATED)
[ "Step 1: 18 - 41 = -23\nStep 2: -23 + 83 = 60\nStep 3: 60 * 18 = 1080\nStep 4: 1080 - 83 = 109" ]
[ false ]
[ "Line uses unavailable numbers: Step 2: -23 + 83 = 60" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 18 - 41 = -23\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)
0
[false]
samples_countdown4arg_2025-07-08T06-42-16.984912.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 arithmetic ope(...TRUNCATED)
2
0
Step 1: 46 * 100 = 4600 Step 2: 4600 - 28 = 4572 Step 3: 4572 + 30 = 204
"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: 4572 + 30 = 204
[ [ "Step 1: 46 * 100 = 4600\nStep 2: 4600 - 28 = 4572\nStep 3: 4572 + 30 = 204" ] ]
[ [ false ] ]
[ [ "Incorrect arithmetic in line: Step 3: 4572 + 30 = 204" ] ]
[ [ "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [28, 100, 30, 46] and the arithmetic op(...TRUNCATED)
[ "Step 1: 46 * 100 = 4600\nStep 2: 4600 - 28 = 4572\nStep 3: 4572 + 30 = 204" ]
[ false ]
[ "Incorrect arithmetic in line: Step 3: 4572 + 30 = 204" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 46 * 100 = 4600\nSt(...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_2025-07-08T06-42-16.984912.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve the problem using the numbers [77, 22, 93, 46] an(...TRUNCATED)
countdown
"<think>\nTo solve the problem using the numbers [77, 22, 93, 46] and the operations (+, -, *, /), w(...TRUNCATED)
3
0
Step 1: 93 * (77 - 22) = 837
"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: 93 * (77 - 22) = 837
[["Step 1: 93 * (77 - 22) = 837","93*(77 - 22)"],["93*(77 - 22)"],["93*(77 - 22)","Step 1: 93 * 9 = (...TRUNCATED)
[ [ false, false ], [ false ], [ false, false ] ]
[["Incorrect arithmetic in line: Step 1: 93 * (77 - 22) = 837","Expected a single '=' separating exp(...TRUNCATED)
[ [ "", "" ], [ "" ], [ "", "" ] ]
["<think>\nTo solve the problem using the numbers [77, 22, 93, 46] and the operations (+, -, *, /), (...TRUNCATED)
[ "93*(77 - 22)", "93*(77 - 22)", "Step 1: 93 * 9 = 837" ]
[ 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: 93*(77 - 22)\nWas Correct: (...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_2025-07-08T06-42-16.984912.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 [31, 44, 21, 28] that equal(...TRUNCATED)
4
0
Step 1: 44 * 5 = 220 Step 2: 220 + 4 = 224
"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: 44 * 5 = 220
[["Step 1: 44 * 5 = 220\nStep 2: 220 + 4 = 224","Step 1: 21 * 28 = 588\nStep 2: 588 - 31 = 557\nStep(...TRUNCATED)
[ [ false, false, false ] ]
[["Line uses unavailable numbers: Step 1: 44 * 5 = 220","Line uses unavailable numbers: Step 3: 557 (...TRUNCATED)
[ [ "", "", "" ] ]
["<think>\nTo solve the problem of creating an equation using the numbers [31, 44, 21, 28] that equa(...TRUNCATED)
[ "Step 1: 44 - 21 = 23\nStep 2: 23 * 10 = 230\nStep 3: 230 - 6 = 224" ]
[ false ]
[ "Line uses unavailable numbers: Step 2: 23 * 10 = 230" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 44 - 21 = 23\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)
1
[true]
samples_countdown4arg_2025-07-08T06-42-16.984912.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" ] ]
[ [ 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" ]
[ 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_2025-07-08T06-42-16.984912.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 the arithmetic oper(...TRUNCATED)
6
0
Step 1: 95 - 29 = 66 Step 2: 66 + 37 = 110
"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 2: 66 + 37 = 110
[["Step 1: 95 - 29 = 66\nStep 2: 66 + 37 = 110","Step 1: 95 - 29 = 66\nStep 2: 66 + 81 = 110","81 + (...TRUNCATED)
[[false,false,false],[false],[false,false],[false,true,false,false,true,true,false],[true,false],[tr(...TRUNCATED)
[["Incorrect arithmetic in line: Step 2: 66 + 37 = 110","Incorrect arithmetic in line: Step 2: 66 + (...TRUNCATED)
[ [ "", "", "" ], [ "" ], [ "", "" ], [ "", "", "", "", "", "", "" ], [ "", "" ], [ "", "" ] ]
["<think>\nTo solve this problem, we need to use the numbers [81, 29, 95, 37] and the arithmetic ope(...TRUNCATED)
[ "81 + 95 - 29", "", "81 + 95 - 29", "81 + 95 - 29", "81 + 95 - 37", "81 + 95 - 37" ]
[ false, false, false, false, false, false ]
["Expected a single '=' separating expression and result","No answer","Expected a single '=' separat(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 81 + 95 - 29\nWas Correct: (...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_2025-07-08T06-42-16.984912.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to combine the given number(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to combine the given numbers [65, 56, 37, 12] using basic a(...TRUNCATED)
7
0
Step 1: 65 * 12 = 800 Step 2: 56 + 37 = 93 Step 3: 800 + 93 = 893 Step 4: 893 + 3 = 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 1: 65 * 12 = 800
[["Step 1: 65 * 12 = 800\nStep 2: 56 + 37 = 93\nStep 3: 800 + 93 = 893\nStep 4: 893 + 3 = 896","Step(...TRUNCATED)
[ [ false, false, false, false, false, false, false, false, false, false, false, false, false ] ]
[["Incorrect arithmetic in line: Step 1: 65 * 12 = 800","Incorrect arithmetic in line: Step 2: 121 *(...TRUNCATED)
[ [ "", "", "", "", "", "", "", "", "", "", "", "", "" ] ]
["<think>\nTo solve this problem, we need to combine the given numbers [65, 56, 37, 12] using basic (...TRUNCATED)
[ "Step 1: 65 - 56 = 9\nStep 2: 9 + 37 = 46\nStep 3: 46 * 12 = 552" ]
[ false ]
[ "Incorrect final answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: Step 1: 65 - 56 = 9\nStep 2(...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_2025-07-08T06-42-16.984912.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [4, 13, (...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [4, 13, 64, 60] and the arithmetic opera(...TRUNCATED)
8
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 [4, 13, 64, 60] and the arithmetic oper(...TRUNCATED)
[ "" ]
[ false ]
[ "No answer" ]
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: \nWas Correct: False\n\nTar(...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_2025-07-08T06-42-16.984912.jsonl
"[{\"budget_forced_chunks\": [\"<think>\\nTo solve this problem, we need to use the numbers [62, 56,(...TRUNCATED)
countdown
"<think>\nTo solve this problem, we need to use the numbers [62, 56, 32, 55] and the operations (+, (...TRUNCATED)
9
0
Step 1: 62 + 56 = 118 Step 2: 118 - 32 = 86 Step 3: 86 * 55 = 4670
"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: 86 * 55 = 4670
[["Step 1: 62 + 56 = 118\nStep 2: 118 - 32 = 86\nStep 3: 86 * 55 = 4670","Step 1: 62 - 56 = 6\nStep (...TRUNCATED)
[[false,false,false,false],[false,false,false,false,false,false,false,false,false,false,false,false,(...TRUNCATED)
[["Incorrect arithmetic in line: Step 3: 86 * 55 = 4670","Incorrect arithmetic in line: Step 3: 192 (...TRUNCATED)
[["","","",""],["","","","","","","","","","","","","","","","","","","","","","","","","","","","",(...TRUNCATED)
["<think>\nTo solve this problem, we need to use the numbers [62, 56, 32, 55] and the operations (+,(...TRUNCATED)
[ "32*(62 - 56)", "32*(62 - 56) / 55" ]
[ false, false ]
["Expected a single '=' separating expression and result","Expected a single '=' separating expressi(...TRUNCATED)
{"content":["Initial Response\n\nEval Type: countdown\nExtracted Answer: 32*(62 - 56)\nWas Correct: (...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
7