Dataset Viewer
Auto-converted to Parquet Duplicate
conversations
listlengths
2
2
question
null
source
stringclasses
1 value
id
int64
28.3k
28.3k
prompt
listlengths
2
2
answer
stringclasses
1 value
prompt__example_annotation__metadata
dict
task_source
stringclasses
1 value
task_config
stringclasses
1 value
model_responses__example_annotation
listlengths
1
1
model_responses__example_annotation__eval_is_correct
listlengths
1
1
model_responses__example_annotation__eval_extracted_answers
listlengths
1
1
prompt_type
stringclasses
2 values
reflection_prompt
listlengths
2
2
model_responses__mutated_prompts_reflection
listlengths
1
1
model_responses__mutated_prompts_reflection__finish_reason_length_flags
listlengths
1
1
model_responses__mutated_prompts_reflection__length_partial_responses
listlengths
1
1
reflection_prompt__mutated_prompts_reflection__metadata
dict
model_responses__mutated_prompts_reflection__metadata
dict
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: \nCalculate the percentage of the unscreened part of a TV with total sides 6 * 5 and screen size 5 * 4.\n\nStep 1: Calculate the area of the total side.\nTotal area = 6 * 5 = 30 square units.\n\nStep 2: Calculate the area of the screen.\nScreen area = 5 * 4 = 20 square units.\n\nStep 3: Calcula...
[ false ]
[ "33.33" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The problem involves calculating the percentage of the unscreened part of a TV. The provided solution correctly calculates the areas and percentages involved. It starts by finding the total area of the sides (30 square units) and the screen area (20 square units). It then finds the unscr...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: \nCalculate the percentage of the unscreened part of a television where the total side area is 6 * 5 and the screen area is 5 * 4.\n\nStep 1: Calculate the total area.\nTotal area = 6 * 5\n\nStep 2: Calculate the screen area.\nScreen area = 5 * 4\n\nStep 3: Calculate the unscreened area.\nUnscr...
[ false ]
[ "(1) Total area = 30\n(2) Screen area = 20\n(3) Unscreened area = 30 - 20 = 10\n(4) Percentage of unscreened part = (10 / 30) * 100 = 33.33%" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The model has incorrectly rewritten the original question into a completely unrelated calculation involving areas of a television. It did not address the actual question asked about the function \\(f(x)\\) applied to \\(\\lg 81\\). Instead, it provided calculations for a different proble...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: Given \\( n \\) tables and an average dining time of \\( \\bar{t} \\) minutes per table, find the average waiting time for a customer if all tables are occupied.\n\nStep 1: Understand that since all tables are occupied, new customers will have to wait until one of the current diners leaves.\nSt...
[ false ]
[ "\\(\\frac{\\bar{t}}{n}\\)" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The original question asks to find the average waiting time for a customer when all tables are occupied and each table has an average dining time of \\(\\bar{t}\\). The solution provided correctly identifies that the average waiting time is \\(\\frac{\\bar{t}}{n}\\), where \\(n\\) is the...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: Given \\( n \\) tables each with an average dining time of \\( \\bar{t} \\) minutes, find the average waiting time for a customer assuming all tables are occupied and arrivals/departures are random.\n\nStep 1: Understand that since all tables are occupied, there will be no empty seats available...
[ false ]
[ "\\(\\frac{\\bar{t}}{2}\\)" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The model correctly identified the average waiting time for a customer as \\(\\frac{\\bar{t}}{2}\\) based on the uniform distribution of waiting times between 0 and \\(\\bar{t}\\). This calculation is accurate because the expected value of a uniform distribution U(a, b) is given by \\(\\...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: \nIf each child originally gets 2 bananas but due to 360 children being absent, each of the remaining children gets 4 bananas, find the total number of children when all are present.\n\nStep 1: Let's denote the original number of children as \\(x\\).\nStep 2: When 360 children are absent, the n...
[ false ]
[ "(720)" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The rewritten question asks us to find the original number of children based on changes in banana distribution due to some children being absent. The solution correctly sets up equations based on the initial and adjusted conditions, solves them, and arrives at the conclusion that the ori...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "Out of the 120 people who attended the party, 1/3 are men while x% are women. The rest are children. How many children attended the party?\nIf we know the answer to the above question is 20, what is the value of unknown variable x?" }, { "from": "assistant", "value": ...
null
tiger_math
28,288
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Out of the 120 people who atten...
50
{ "api_url": "http://10.32.36.236:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 2, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
openthoughts
openthoughts
[ "Rewritten Question: \nIf each child originally gets 2 bananas but due to 360 children being absent, each of the remaining children gets 4 bananas, find the total number of children when all are present.\n\nStep 1: Let's denote the original number of children as \\( x \\).\nStep 2: Initially, if there were no absen...
[ false ]
[ "(E) 720" ]
rephrase
[ { "content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo...
[ "Let us verify this answer. The problem involves determining the number of children initially when some are absent. The model correctly sets up the equation based on the number of bananas and solves for the initial number of children, arriving at 720. This aligns with the logical steps provided.\n\n<verdict>\nCorre...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.196:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 512, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"Out of the 120 people who attended the party, 1/3 are men while x% are wome(...TRUNCATED)
null
tiger_math
28,288
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
50
{"api_url":"http://10.32.36.236:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Find all possible pairs \\((x, y)\\) of positive integers such that \\(x^2 + y(...TRUNCATED)
[ false ]
[ "No solution" ]
rephrase
[{"content":"You think step by step and reflect on the given answer for the question reasoning about(...TRUNCATED)
["Let us verify this answer. The original problem involves solving a system of equations involving s(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.196:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"Out of the 120 people who attended the party, 1/3 are men while x% are wome(...TRUNCATED)
null
tiger_math
28,288
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
50
{"api_url":"http://10.32.36.236:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Find all possible pairs \\((x, y)\\) of positive integers such that \\(x^2 + y(...TRUNCATED)
[ false ]
[ "No solution exists." ]
rephrase
[{"content":"You think step by step and reflect on the given answer for the question reasoning about(...TRUNCATED)
["Let us verify this answer... The original problem asks to find pairs \\((x, y)\\) of positive inte(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.196:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"Out of the 120 people who attended the party, 1/3 are men while x% are wome(...TRUNCATED)
null
tiger_math
28,288
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
50
{"api_url":"http://10.32.36.236:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Simplify $\\left(\\dfrac{1+i}{\\sqrt{2}}\\right)^{10}-\\left(\\dfrac{1-i}{\\sq(...TRUNCATED)
[ true ]
[ "2i" ]
rephrase
[{"content":"You think step by step and reflect on the given answer for the question reasoning about(...TRUNCATED)
["Let us verify this answer... The rewritten question involves simplifying a complex expression usin(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.196:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"Out of the 120 people who attended the party, 1/3 are men while x% are wome(...TRUNCATED)
null
tiger_math
28,288
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
50
{"api_url":"http://10.32.36.236:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Simplify $\\left(\\dfrac{1+i}{\\sqrt{2}}\\right)^{10}-\\left(\\dfrac{1-i}{\\sq(...TRUNCATED)
[ true ]
[ "2i" ]
rephrase
[{"content":"You think step by step and reflect on the given answer for the question reasoning about(...TRUNCATED)
["Let us verify this answer. The model correctly identified the magnitudes and angles of the complex(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.196:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
4