Dataset Viewer
Auto-converted to Parquet Duplicate
conversations
listlengths
2
2
question
null
source
stringclasses
1 value
id
int64
36.4k
36.4k
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": "In a small zoo, there are bunnies and parrots. If there are 4 times as many parrots as bunnies and together their combined number of legs and wings is 160, how many parrots are there in the zoo?" }, { "from": "assistant", "value": "<think>\nOkay, let's see. I need to ...
null
tiger_math
36,371
[ { "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": "In a small zoo, there are bunni...
32
{ "api_url": "http://10.32.36.232:9080/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 \\( P(A) = 0.8 \\), \\( P(B) = 0.7 \\), and \\( P(A \\cup B) = 0.9 \\), find \\( P(A \\Delta B) \\).\n\nStep 1: Recall the formula for the symmetric difference (exactly one of the events occurs):\n\\[ P(A \\Delta B) = P(A) + P(B) - 2P(A \\cap B) \\]\n\nStep 2: Use the inclusion-exclusion ...
[ true ]
[ "0.3" ]
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 asked to find \\( P(A \\Delta B) \\) given probabilities for sets A and B. The steps provided seem logically sound, starting with recalling the symmetric difference formula and using the inclusion-exclusion principle to find \\( P(A \\cap B) \\). The calculations ap...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.231:10080/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_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "In a small zoo, there are bunnies and parrots. If there are 4 times as many parrots as bunnies and together their combined number of legs and wings is 160, how many parrots are there in the zoo?" }, { "from": "assistant", "value": "<think>\nOkay, let's see. I need to ...
null
tiger_math
36,371
[ { "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": "In a small zoo, there are bunni...
32
{ "api_url": "http://10.32.36.232:9080/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: Calculate the cumulative return of a triple-leveraged ETF given daily returns of 5% and -2%.\n\nStep 1: Understand that for a triple-leveraged ETF, the daily return is tripled.\nStep 2: Calculate the tripled returns for each day.\n- For the first day, the tripled return is \\(3 \\times 0.05 = 0...
[ false ]
[ "(8.1)" ]
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 response incorrectly calculates the cumulative return of a triple-leveraged ETF given daily returns of 5% and -2%. It triples the daily returns, converts them to factors, multiplies these factors, and then subtracts 1 to get the return percentage. However, the definition of cum...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.231:10080/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_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "In a small zoo, there are bunnies and parrots. If there are 4 times as many parrots as bunnies and together their combined number of legs and wings is 160, how many parrots are there in the zoo?" }, { "from": "assistant", "value": "<think>\nOkay, let's see. I need to ...
null
tiger_math
36,371
[ { "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": "In a small zoo, there are bunni...
32
{ "api_url": "http://10.32.36.232:9080/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: Calculate the cumulative return of a triple-leveraged ETF given daily returns of 5% and -2%.\n\nStep 1: Understand that for a leveraged ETF, the return is not simply tripled but rather compounded.\nStep 2: The formula for compound return when there are multiple periods is \\( (1 + R_1)(1 + R_2)...
[ false ]
[ "(1 + 0.05)(1 - 0.02) - 1 = 1.05 * 0.98 - 1 = 1.029 - 1 = 0.029" ]
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 response calculates the cumulative return of a triple-leveraged ETF based on daily returns of 5% and -2%, and arrives at a cumulative return of 2.9%. However, the problem does not specify that the ETF is triple-leveraged, so the calculation assumes a simple compounding of retur...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.231:10080/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_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "In a small zoo, there are bunnies and parrots. If there are 4 times as many parrots as bunnies and together their combined number of legs and wings is 160, how many parrots are there in the zoo?" }, { "from": "assistant", "value": "<think>\nOkay, let's see. I need to ...
null
tiger_math
36,371
[ { "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": "In a small zoo, there are bunni...
32
{ "api_url": "http://10.32.36.232:9080/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: Erin counts six trolls by the path. There are 6 less than four times that number of trolls under the bridge. There are half as many trolls in the plains as under the bridge. Total troll count?\n\nStep 1: Calculate the number of trolls under the bridge.\nNumber of trolls by the path = 6\nTrolls ...
[ false ]
[ "6 + (4*6-6) + ((4*6-6)/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 response provided a rewritten question involving trolls, followed by a series of steps to calculate the total number of trolls. The final expression provided matches the logical steps described, and the calculation appears to be accurate based on the information given. The expr...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.231:10080/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_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[ { "from": "user", "value": "In a small zoo, there are bunnies and parrots. If there are 4 times as many parrots as bunnies and together their combined number of legs and wings is 160, how many parrots are there in the zoo?" }, { "from": "assistant", "value": "<think>\nOkay, let's see. I need to ...
null
tiger_math
36,371
[ { "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": "In a small zoo, there are bunni...
32
{ "api_url": "http://10.32.36.232:9080/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: Erin counts six trolls by the path. There are 6 less than four times that number of trolls under the bridge. There are half as many trolls in the plains as under the bridge. Total trolls counted = ?\n\nStep 1: Calculate the number of trolls under the bridge.\nNumber of trolls under the bridge =...
[ false ]
[ "6 + 18 + 9\n= 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 rewritten question asks for the total number of trolls, including those by the path, under the bridge, and in the plains. According to the steps provided, the calculation is correct:\n\n- Trolls by the path = 6\n- Trolls under the bridge = 4 * 6 - 6 = 24 - 6 = 18\n- Trolls in the pla...
[ false ]
[ "" ]
{ "api_url": "http://10.32.36.231:10080/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_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"In a small zoo, there are bunnies and parrots. If there are 4 times as many(...TRUNCATED)
null
tiger_math
36,371
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
32
{"api_url":"http://10.32.36.232:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Given a function \\( f: [a, \\infty) \\rightarrow \\mathbb{R} \\) that is cont(...TRUNCATED)
[ false ]
[ "\\(\\delta = \\min\\left( \\delta_0, \\frac{\\epsilon}{2M - a} \\right)" ]
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 question pertained to finding the largest possible value o(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.231:10080/v1","backend":"litellm","chat_template_applied":true,"generati(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"In a small zoo, there are bunnies and parrots. If there are 4 times as many(...TRUNCATED)
null
tiger_math
36,371
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
32
{"api_url":"http://10.32.36.232:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Given a function \\( f: [a, \\infty) \\rightarrow \\mathbb{R} \\) that is cont(...TRUNCATED)
[ false ]
["\\(\\delta\\) depends on \\( \\epsilon \\) and the behavior of \\( f \\) on \\([a, M]\\), but gene(...TRUNCATED)
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 response discusses finding the largest possible \\(\\delta\\)(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.231:10080/v1","backend":"litellm","chat_template_applied":true,"generati(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"In a small zoo, there are bunnies and parrots. If there are 4 times as many(...TRUNCATED)
null
tiger_math
36,371
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
32
{"api_url":"http://10.32.36.232:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Determine the minimum number of colors needed to color the vertices of a graph(...TRUNCATED)
[ false ]
[ "5" ]
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 asks for the minimum number of colors needed to (...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.231:10080/v1","backend":"litellm","chat_template_applied":true,"generati(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"In a small zoo, there are bunnies and parrots. If there are 4 times as many(...TRUNCATED)
null
tiger_math
36,371
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
32
{"api_url":"http://10.32.36.232:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: Determine the minimum number of colors needed to color a graph with 12 vertice(...TRUNCATED)
[ true ]
[ "4" ]
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 response correctly identifies the application of Brooks' Theo(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.231:10080/v1","backend":"litellm","chat_template_applied":true,"generati(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-7B-Instruct", "n_responses": 1 }
[{"from":"user","value":"In a small zoo, there are bunnies and parrots. If there are 4 times as many(...TRUNCATED)
null
tiger_math
36,371
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
32
{"api_url":"http://10.32.36.232:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
openthoughts
openthoughts
["Rewritten Question: \nCalculate the percentage of the unscreened part of a TV where the total side(...TRUNCATED)
[ false ]
[ "( (6*5 - 5*4) / (6*5) ) * 100" ]
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 response provides the calculation steps for finding the perce(...TRUNCATED)
[ false ]
[ "" ]
{"api_url":"http://10.32.36.231:10080/v1","backend":"litellm","chat_template_applied":true,"generati(...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
3