Datasets:

Modalities:
Text
Formats:
parquet
Libraries:
Datasets
pandas
Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
974
977
answer
stringlengths
6
13
task_config
stringclasses
1 value
task_source
stringclasses
1 value
prompt
listlengths
2
2
model_responses
listlengths
64
64
model_responses__eval_is_correct
listlengths
64
64
prompt_type
stringclasses
3 values
metadata
stringlengths
115
125
is_model_response_correct__final_answer
listlengths
64
64
is_model_response_correct__reasoning
listlengths
64
64
model_responses__example_annotation
listlengths
16
16
model_responses__example_annotation__finish_reason_length_flags
listlengths
16
16
model_responses__example_annotation__length_partial_responses
listlengths
16
16
prompt__example_annotation__metadata
dict
model_responses__example_annotation__metadata
dict
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>. # Problem Using the numbers in the list [84, 78, 27], create an equation that equals 135. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target. Give your answer in the following format: <answer> (your answer) </answer> Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target. For example: If the list of numbers was [1, 2, 3] and the target was 1, you could write: <answer> Step 1: 1 + 2 = 3 Step 2: 3 / 3 = 1 </answer> or <answer> (1 + 2) / 3 </answer> Let's think step by step.
78 - 27 + 84
countdown_3arg
countdown
[ { "content": "You like to solve problems by understanding the problem, writing a plan, executing the plan, then giving an answer. Write a plan that when reasoned over would solve the question then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end witho...
[ "To solve this problem, we need to use the numbers [84, 78, 27] and apply basic arithmetic operations (+, -, *, /) to reach the target number 135. Let's break it down:\n\n1. Start with the number 84.\n2. We need to get closer to 135, so let's try to subtract something from 84.\n3. Subtract 27 from 84: 84 - 27 = 57\...
[ true, false, false, true, false, false, false, true, false, false, false, true, true, true, true, false, false, true, true, true, false, false, false, true, true, false, false, false, false, false, true, false, false, true, false, true, true, ...
plan_and_execute_rationalized
{"source_dataset": "countdown", "source_index": 3316, "numbers": [84, 78, 27], "target": 135, "expression": "78 - 27 + 84"}
[ "Step 1: 84 - 27 = 57\nStep 2: 57 + 78 = 135", "Step 1: 84 + 78 = 162\nStep 2: 162 * 27 = 4394\nStep 3: 4394 / 32 = 137.25", "Step 1: 84 * 78 = 6432\nStep 2: 6432 - 507 = 135", "Step 1: 84 + 78 = 162\nStep 2: 162 - 27 = 135", "Step 1: 2268 - 135 = 2133\nStep 2: 2133 / 78 = 27", "Step 1: 84 * 1.625 = 135\n...
[ null, "Incorrect arithmetic in line: Step 2: 162 * 27 = 4394", "Incorrect arithmetic in line: Step 1: 84 * 78 = 6432", null, "Line uses unavailable numbers: Step 1: 2268 - 135 = 2133", "Incorrect arithmetic in line: Step 1: 84 * 1.625 = 135", "Line uses unavailable numbers: Step 2: 57 * 2 = 114", null...
[ "First, I'll try to understand the problem better by writing out a plan and going really deep into detail about how I should solve this.\n\nUpon analyzing the given list of numbers [84, 78, 27], my initial thought is that we need to combine these numbers using basic arithmetic operations (+, -, *, /) to get as clos...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://10.32.36.216:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 4, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "prompt": [ { "content": "You like to solve problems by understanding the problem, writing a plan, executing the plan, then giving an answer. Write a plan that when reasoned over would solve the question then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer. You will never mention the hint at all, otherwise you will be penalyzed. For example, do not say \"However, based on the hint provided, the correct answer should be\" instead say \"However, this does not feel right... maybe I should try again\", then try to reason toward the hinted answer without saying that it exists.", "role": "system" }, { "content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [84, 78, 27], create an equation that equals 135. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nTo solve this question, write a high level plan you intend to use starting with \"First, I'll try to understand the problem better by writing out a plan and go really deep into detail about how I should solve this.\", then execute that plan (whatever reasoning is required), then give your resulting equation or number as the answer in the \"<answer>\n(your answer)\n</answer>\" tag.\n\nHint: the answer is 78 - 27 + 84. Pretend you did not see this and instead reason to this answer.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
83*(96 - 89)
countdown_3arg
countdown
[{"content":"You like to solve problems by understanding the problem, writing a plan, executing the (...TRUNCATED)
["To solve this problem, we need to use the numbers [96, 83, 89] and the operations (+, -, *, /) to (...TRUNCATED)
[false,true,false,true,true,false,false,false,false,false,true,false,true,false,false,true,true,fals(...TRUNCATED)
plan_and_execute_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 3317, \"numbers\": [96, 83, 89], \"target\": (...TRUNCATED)
["Step 1: 96 - 83 = 13\nStep 2: 13 * 89 = 1157\nStep 3: 1157 / 2 = 578.5\nStep 4: 578.5 + 2.5 = 581"(...TRUNCATED)
["Line uses unavailable numbers: Step 3: 1157 / 2 = 578.5",null,"Line uses unavailable numbers: Step(...TRUNCATED)
["First, I'll try to understand the problem better by writing out a plan and going really deep into (...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
85 + 58 + 72
countdown_3arg
countdown
[{"content":"You like to solve problems by understanding the problem, writing a plan, executing the (...TRUNCATED)
["To solve this problem, we need to use the numbers [72, 85, 58] and apply basic arithmetic operatio(...TRUNCATED)
[false,false,true,true,true,false,false,false,false,false,false,false,false,true,true,false,false,tr(...TRUNCATED)
plan_and_execute_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 3318, \"numbers\": [72, 85, 58], \"target\": (...TRUNCATED)
["Step 1: 143 * 1.5 = 215","Step 1: 58 + 85 = 143\nStep 2: 143 * 1.5 = 215","Step 1: 85 + 58 = 143\n(...TRUNCATED)
["Incorrect arithmetic in line: Step 1: 143 * 1.5 = 215","Incorrect arithmetic in line: Step 2: 143 (...TRUNCATED)
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
65*5 - 71
countdown_3arg
countdown
[{"content":"You like to solve problems by understanding the problem, writing a plan, executing the (...TRUNCATED)
["To solve the problem of creating an equation using the numbers [65, 5, 71] that equals 254, we nee(...TRUNCATED)
[false,false,true,false,false,false,false,false,true,false,true,false,false,false,false,true,false,f(...TRUNCATED)
plan_and_execute_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 3319, \"numbers\": [65, 5, 71], \"target\": 2(...TRUNCATED)
["Step 1: 396 / 1.5 = 264\nStep 2: 264 - 10 = 254","Step 1: 65 * 5 = 325\nStep 2: 325 + 71 = 254","S(...TRUNCATED)
["Line uses unavailable numbers: Step 1: 396 / 1.5 = 264","Incorrect arithmetic in line: Step 2: 325(...TRUNCATED)
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
76 + 85 + 60
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve the problem, we need to use the numbers [60, 76, 85] and the arithmetic operations (+, -,(...TRUNCATED)
[false,false,true,false,true,true,false,false,false,false,false,false,false,true,false,false,false,t(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1641, \"numbers\": [60, 76, 85], \"target\": (...TRUNCATED)
["Step 1: 221 = 85 - 60 + 76","Step 1: 76 * 85 = 6460\nStep 2: 6460 - 60 = 6400\nStep 3: 6400 + 85 =(...TRUNCATED)
["Could not evaluate line: Step 1: 221 = 85 - 60 + 76","Line uses unavailable numbers: Step 3: 6400 (...TRUNCATED)
["Rewritten Question: Using the numbers 60, 76, and 85, find an equation that equals 221.\n\nStep 1:(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
2*67 - 34
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve this problem, we need to use the numbers [2, 34, 67] and the arithmetic operations (+, -,(...TRUNCATED)
[true,false,false,false,false,false,false,false,true,false,true,false,false,false,false,false,false,(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1642, \"numbers\": [2, 34, 67], \"target\": 1(...TRUNCATED)
["Step 1: 67 * 2 = 134\nStep 2: 134 - 34 = 100","Step 1: 2 + 34 = 36\nStep 2: 36 * 67 = 2412\nStep 3(...TRUNCATED)
[null,"Line uses unavailable numbers: Step 3: 2412 - 2402 = 10","Line uses unavailable numbers: Step(...TRUNCATED)
["Rewritten Question: Using the numbers 2, 34, and 67, create an equation that equals 100 using basi(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
92*(17 - 9)
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve the problem, we need to use the numbers [17, 92, 9] and the operations (+, -, *, /) to ge(...TRUNCATED)
[false,false,false,false,false,false,true,false,false,false,false,false,false,false,false,false,fals(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1643, \"numbers\": [17, 92, 9], \"target\": 7(...TRUNCATED)
["Step 1: 92 * 9 = 828\nStep 2: 828 + 17 = 845\nStep 3: 845 + 17 = 862","Step 1: 92 * 9 = 828\nStep (...TRUNCATED)
["Line uses unavailable numbers: Step 3: 845 + 17 = 862","Line uses unavailable numbers: Step 2: 828(...TRUNCATED)
["Rewritten Question: Use the numbers 17, 92, and 9 to create an equation that equals 736 using basi(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
71 + 25 + 56
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve the problem of creating an equation using the numbers [56, 71, 25] that equals 152, we ne(...TRUNCATED)
[true,false,false,false,false,false,false,false,false,false,false,false,true,true,false,false,false,(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1645, \"numbers\": [56, 71, 25], \"target\": (...TRUNCATED)
["Step 1: 56 + 25 = 81\nStep 2: 81 + 71 = 152","Step 1: 56 * 71 = 3976\nStep 2: 3976 - 25 = 3951\nSt(...TRUNCATED)
[null,"Incorrect arithmetic in line: Step 3: 3951 / 56 = 70.26785714285714","Line uses unavailable n(...TRUNCATED)
["Rewritten Question: Given the numbers 56, 71, and 25, find two equations using basic arithmetic op(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
59*7 - 88
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve this problem, we need to use the numbers [59, 7, 88] and the arithmetic operations (+, -,(...TRUNCATED)
[false,false,false,false,false,false,false,false,true,false,false,true,false,false,false,false,false(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1646, \"numbers\": [59, 7, 88], \"target\": 3(...TRUNCATED)
["Step 1: 59 * 5 = 295\nStep 2: 295 + 30 = 325","Step 1: 59 * 7 = 413\nStep 2: 413 + 88 = 421\nStep (...TRUNCATED)
["Line uses unavailable numbers: Step 1: 59 * 5 = 295","Incorrect arithmetic in line: Step 2: 413 + (...TRUNCATED)
["Rewritten Question: Given the numbers 59, 7, and 88, find a combination of addition, subtraction, (...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
97 - 52 + 87
countdown_3arg
countdown
[{"content":"You answer questions by saying \"Rewritten Question: \" then rewriting the question to (...TRUNCATED)
["To solve the problem, we need to use the numbers [52, 87, 97] and the operations (+, -, *, /) to r(...TRUNCATED)
[true,true,false,false,false,false,true,true,false,false,true,true,false,false,false,true,false,true(...TRUNCATED)
rephrase_rationalized
"{\"source_dataset\": \"countdown\", \"source_index\": 1647, \"numbers\": [52, 87, 97], \"target\": (...TRUNCATED)
["Step 1: 97 - 52 = 45\nStep 2: 87 + 45 = 132","Step 1: 97 - 52 = 45\nStep 2: 45 + 87 = 132","Step 1(...TRUNCATED)
[null,null,"Line uses unavailable numbers: Step 1: 52 * 2 = 104","Incorrect arithmetic in line: Step(...TRUNCATED)
["Rewritten Question: Given the numbers 52, 87, and 97, find a way to combine them using basic arith(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://10.32.36.216:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/meta-llama/Llama-3.2-3B-Instruct", "n_responses": 16 }
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
5