Datasets:

Modalities:
Text
Formats:
parquet
Libraries:
Datasets
pandas
Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
42
688
answer
stringlengths
1
9
task_config
stringclasses
1 value
task_source
stringclasses
1 value
prompt
listlengths
2
2
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
prompt_variant
stringclasses
1 value
original_answer
stringlengths
50
1.01k
task_type
stringclasses
1 value
evaluation_type
stringclasses
1 value
source
stringclasses
1 value
variant
stringclasses
1 value
id
stringlengths
7
10
expected_answer_format
stringclasses
1 value
difficulty
stringclasses
1 value
domain
stringclasses
1 value
model_responses__mutated_prompts
listlengths
16
16
model_responses__mutated_prompts__finish_reason_length_flags
listlengths
16
16
model_responses__mutated_prompts__length_partial_responses
listlengths
16
16
prompt__mutated_prompts__metadata
dict
model_responses__mutated_prompts__metadata
dict
model_responses__mutated_prompts__eval_is_correct
listlengths
16
16
model_responses__mutated_prompts__eval_extracted_answers
listlengths
16
16
model_responses__mutated_prompts__eval_extraction_metadata
listlengths
16
16
model_responses__mutated_prompts__eval_evaluation_metadata
listlengths
16
16
model_responses__mutated_prompts__internal_answers__eval_is_correct
listlengths
16
16
model_responses__mutated_prompts__internal_answers__eval_extracted_answers
listlengths
16
16
model_responses__mutated_prompts__internal_answers__eval_extraction_metadata
listlengths
16
16
model_responses__mutated_prompts__internal_answers__eval_evaluation_metadata
listlengths
16
16
model_responses__mutated_prompts__metrics
dict
Mary is writing a story, and wants her 60 characters to be split according to their initials. Half of her characters have the initial A, and half of this amount have the initial C. Mary wants the rest of her characters to have the initials D and E, but she wants there to be twice as many characters with the initial D a...
10
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
Half the characters have the initial A, which is a total of 60 / 2 = <<60/2=30>>30 characters. This means that 30 / 2 = <<30/2=15>>15 characters have the initial C. Mary wants the remaining 60 – 30 – 15 = <<60-30-15=15>>15 characters to have the initials D or E. For there to be twice as many characters with the initial...
math
numeric_equivalence
gsm8k
main
gsm8k_6154
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Total number of characters\ntotal_characters = 60\n\n# Number of characters with initial A (half of total characters)\ncharacters_A = total_characters / 2\n\n# Number of characters with initial C (half of initial A's)\ncharacters_C = characters_A / 2\n\n# Remaining characters after accounting for A an...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, false, false, false, false, false, false, false, false, false, false, false, false, false, false, true ]
[ "10", null, null, null, null, null, null, null, "40", null, null, null, null, "{characters_D}", null, "10" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "10", "span_end": 949, "span_start": 945, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, ...
[ { "comparison_type": "mathematical", "correct_answer": "10", "evaluation_method": "math_equivalence", "extracted_answer": "10", "extraction_result": null, "is_equivalent": true, "reason": null }, { "comparison_type": null, "correct_answer": null, "evaluation_method": "res...
[ [ true ], [], [], [], [], [], [], [], [ false ], [], [], [], [], [ false ], [], [ true ] ]
[ [ "10" ], [], [], [], [], [], [], [], [ "40" ], [], [], [], [], [ "{characters_D}" ], [], [ "10" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "10", "pattern_used": "answer tag", "position": 945, "span_end": 949, "span_start": 945, "span_text": "10" } ], [], [], [], [], [], [], [], [ { "confidence": 1, ...
[ [ { "comparison_type": "mathematical", "correct_answer": "10", "evaluation_method": "math_equivalence", "extracted_answer": "10", "is_equivalent": true } ], [], [], [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "1...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 2, "pass_at_n": 1, "percent_correct": 0.125, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, ...
Cameron guides tour groups in a museum. He usually answers two questions per tourist. Today, he did four tours. The early morning first group was only 6 people. The following group was a busy group of 11. The third group had 8 people, but one was inquisitive and asked three times as many questions as usual. The last gr...
68
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
Cameron answered 2 * 6 = <<2*6=12>>12 questions for the first group. He answered 2 * 11 = <<2*11=22>>22 questions for the second group. The third group had 8 - 1 = 7 tourists that asked 2 questions each. The third group also had 1 tourist that asked 2 * 3 = <<1*2*3=6>>6 questions. Thus, the third group asked 7 * 2 + 6 ...
math
numeric_equivalence
gsm8k
main
gsm8k_6629
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Number of tourists in each group\ngroup_1 = 6\ngroup_2 = 11\ngroup_3 = 8\ngroup_4 = 7\n\n# Questions answered per tourist\nquestions_per_tourist = 2\n\n# Calculate total questions for each group\ntotal_questions_group_1 = group_1 * questions_per_tourist\ntotal_questions_group_2 = group_2 * questions_p...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null ]
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": n...
[ { "comparison_type": null, "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "is_equivalent": null, "reason": "no_extracted_answer" }, { "comparison_type": null, "correct_answer": ...
null
null
null
null
{ "flips_by": null, "flips_total": null, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ ...
Nick hides 10 chocolates in his closet. His brother Alix hides 3 times as many chocolates than Nick hides. Last night, their mom found and took 5 chocolates from Alix. How many more chocolates does Alix have than Nick?
15
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
Alix has 3 * 10 = <<3*10=30>>30 chocolates. After his mom took 5 chocolates, Alix has now 30 - 5 = <<30-5=25>>25 chocolate. So Alix has 25 - 10 = <<25-10=15>>15 chocolates more than Nick. #### 15
math
numeric_equivalence
gsm8k
main
gsm8k_5342
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Step 1: Calculate how many chocolates Alix initially hid.\nnick_chocolates = 10\nalix_initial_chocolates = nick_chocolates * 3\n\n# Step 2: Subtract the chocolates taken by their mom from Alix's initial count.\nchocolates_taken_by_mom = 5\nalix_final_chocolates = alix_initial_chocolates - chocolates_t...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, true, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, "(15)", null, "4", null, null, null, null, null, null, null, null, null, "-5", null ]
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": n...
[ { "comparison_type": null, "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "is_equivalent": null, "reason": "no_extracted_answer" }, { "comparison_type": null, "correct_answer": ...
[ [], [], [ true ], [], [ false ], [], [], [], [], [], [], [], [], [], [ false ], [] ]
[ [], [], [ "(15)" ], [], [ "4" ], [], [], [], [], [], [], [], [], [], [ "-5" ], [] ]
[ [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "(15)", "pattern_used": "answer tag", "position": 924, "span_end": 930, "span_start": 924, "span_text": "(15)" } ], [], [ { "confidence": 1, "extraction_type...
[ [], [], [ { "comparison_type": "mathematical", "correct_answer": "15", "evaluation_method": "math_equivalence", "extracted_answer": "(15)", "is_equivalent": true } ], [], [ { "comparison_type": "mathematical", "correct_answer": "15", "evaluation_...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.0625, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, ...
Alden's family invited their relatives for a family reunion on Christmas eve. There were 50 more female adults than male adults, and children were twice the total number of adults. If there were 100 male adults, how many people attended the family reunion?
750
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
If the number of female adults was 50 more than the males, then there were 100+50 = <<100+50=150>>150 females. The total number of adults is 150+100 = <<150+100=250>>250 The children were twice the total number of adults, thus 2*250 = <<2*250=500>>500 The total number of people at the family reunion is 500+250 = <<500+...
math
numeric_equivalence
gsm8k
main
gsm8k_1857
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n\n```python\n# Number of male adults\nmale_adults = 100\n\n# Number of female adults\nfemale_adults = male_adults + 50\n\n# Total number of adults\ntotal_adults = male_adults + female_adults\n\n# Children are twice the total number of adults\nchildren = 2 * total_adults\n\n# Total number of people at th...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, null, "450", null, "450", null, null, null, null, null, null, null, null, "300" ]
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": n...
[ { "comparison_type": null, "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "is_equivalent": null, "reason": "no_extracted_answer" }, { "comparison_type": null, "correct_answer": ...
[ [], [], [], [], [ false ], [], [ false ], [], [], [], [], [], [], [], [], [ false ] ]
[ [], [], [], [], [ "450" ], [], [ "450" ], [], [], [], [], [], [], [], [], [ "300" ] ]
[ [], [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "450", "pattern_used": "answer tag", "position": 453, "span_end": 456, "span_start": 453, "span_text": "450" } ], [], [ { "confidence": 1, "extra...
[ [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "750", "evaluation_method": "math_equivalence", "extracted_answer": "450", "is_equivalent": false } ], [], [ { "comparison_type": "mathematical", "correct_answer": "750", ...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, ...
Abigail has a report due tomorrow which needs to be 1000 words in length. Abigail can type 300 words in half an hour. If she has already written 200 words, how many more minutes will it take her to finish the report?
80
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
She needs to type an additional 1000 – 200 = <<1000-200=800>>800 words. In one minute she can type 300 words / 30 = <<300/30=10>>10 words. It will take her 800 / 10 = <<800/10=80>>80 more minutes to finish typing the report. #### 80
math
numeric_equivalence
gsm8k
main
gsm8k_6236
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n\n```python\n# Given data\ntotal_words_needed = 1000\nwords_written_initially = 200\nwords_per_half_hour = 300\n\n# Calculate remaining words needed\nremaining_words_needed = total_words_needed - words_written_initially\n\n# Calculate time taken for writing remaining words (in hours)\ntime_hours_for_rem...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, true, false, false, false, false, false, false, false, false, false ]
[ null, null, null, null, null, "50", "80", "40", "40", null, null, null, null, null, null, "50" ]
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": n...
[ { "comparison_type": null, "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "is_equivalent": null, "reason": "no_extracted_answer" }, { "comparison_type": null, "correct_answer": ...
[ [], [], [], [], [], [ false ], [ true ], [ false ], [ false ], [], [], [], [], [], [], [ false ] ]
[ [], [], [], [], [], [ "50" ], [ "80" ], [ "40" ], [ "40" ], [], [], [], [], [], [], [ "50" ] ]
[ [], [], [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "50", "pattern_used": "answer tag", "position": 1170, "span_end": 1172, "span_start": 1170, "span_text": "50" } ], [ { "confidence": 1, "extr...
[ [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "80", "evaluation_method": "math_equivalence", "extracted_answer": "50", "is_equivalent": false } ], [ { "comparison_type": "mathematical", "correct_answer": "80", "...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.0625, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, ...
Mary is making a spinach quiche. She takes 40 ounces of raw spinach and cooks it until it's 20% of its initial volume. If she mixes the spinach with 6 ounces of cream cheese and 4 ounces of eggs, what is the total volume of the quiche?
18
gsm8k
gsm8k
[ { "content": "You like to solve problems by thinking in python code. Write a python script that 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.", "role": "system" }, { "content": "An...
[]
[]
python_prog
First find the cooked volume of the spinach: 40 ounces * 20% = <<40*20*.01=8>>8 ounces Then add that to the volume of the other ingredients to find the total volume: 8 ounces + 6 ounces + 4 ounces = <<8+6+4=18>>18 ounces #### 18
math
numeric_equivalence
gsm8k
main
gsm8k_5863
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Initial volume of raw spinach\ninitial_spinach_volume = 40\n\n# Volume after cooking (20% of initial volume)\ncooked_spinach_volume = initial_spinach_volume * 0.20\n\n# Amounts of ingredients mixed into the cooked spinach\ncream_cheese_amount = 6\neggs_amount = 4\n\n# Total volume of the quiche\ntotal...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:45035", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 16, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/Qw...
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "120.0", null, null, null, null, null, "42", null, null, null, null, null, "130", null, null, null ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "120.0", "span_end": 472, "span_start": 467, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, ...
[ { "comparison_type": "mathematical", "correct_answer": "18", "evaluation_method": "math_equivalence", "extracted_answer": "120.0", "extraction_result": null, "is_equivalent": false, "reason": null }, { "comparison_type": null, "correct_answer": null, "evaluation_method": ...
[ [ false ], [], [], [], [], [], [ false ], [], [], [], [], [], [ false ], [], [], [] ]
[ [ "120.0" ], [], [], [], [], [], [ "42" ], [], [], [], [], [], [ "130" ], [], [], [] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "120.0", "pattern_used": "answer tag", "position": 467, "span_end": 472, "span_start": 467, "span_text": "120.0" } ], [], [], [], [], [], [ { "confidence": 1, "e...
[ [ { "comparison_type": "mathematical", "correct_answer": "18", "evaluation_method": "math_equivalence", "extracted_answer": "120.0", "is_equivalent": false } ], [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "18", ...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, ...
"Brendan works online and is paid every week. Once he gets the money, he recharges his debit card wi(...TRUNCATED)
1000
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"The total amount of money used to charge the debit card is 1/2*$5000 = $<<1/2*5000=2500>>2500.\nWhe(...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_6882
boxed_number
elementary_math
arithmetic_word_problems
["```python\n\n```python\n# Given data\nweekly_earnings = 5000\ncar_cost = 1500\n\n# Brendan's weekl(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:45035","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, "2250.0", null, null, null, null, null, "1450", null, null, "2500", null, null, "8750.0" ]
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"comparison_type":null,"correct_answer":null,"evaluation_method":"response_processor","extracted_a(...TRUNCATED)
[ [], [], [], [ false ], [], [], [], [], [], [ false ], [], [], [ false ], [], [], [ false ] ]
[ [], [], [], [ "2250.0" ], [], [], [], [], [], [ "1450" ], [], [], [ "2500" ], [], [], [ "8750.0" ] ]
[[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"2250.0","pattern_used":"a(...TRUNCATED)
[[],[],[],[{"comparison_type":"mathematical","correct_answer":"1000","evaluation_method":"math_equiv(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent(...TRUNCATED)
"Haruto has tomato plants in his backyard. This year the plants grew 127 tomatoes. Birds had eaten 1(...TRUNCATED)
54
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"After the birds ate 19 of the tomatoes Haruto has 127 - 19 = <<127-19=108>>108 tomatoes left.\nAfte(...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_582
boxed_number
elementary_math
arithmetic_word_problems
["```python\n# Total tomatoes grown\ntotal_tomatoes = 127\n\n# Tomatoes eaten by birds\ntomatoes_eat(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:45035","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, null, null, null, null, null, null, null, null, "65", null, null, null, null ]
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"comparison_type":null,"correct_answer":null,"evaluation_method":"response_processor","extracted_a(...TRUNCATED)
[ [], [], [], [], [], [], [], [], [], [], [], [ false ], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [], [], [ "65" ], [], [], [], [] ]
[[],[],[],[],[],[],[],[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"6(...TRUNCATED)
[[],[],[],[],[],[],[],[],[],[],[],[{"comparison_type":"mathematical","correct_answer":"54","evaluati(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent(...TRUNCATED)
"James drives to Canada at 60 mph. It is a distance of 360 miles. He has a 1 hour stop along the w(...TRUNCATED)
7
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"He spends 360/60=<<360/60=6>>6 hours driving\nThat means the trip takes 6+1=<<6+1=7>>7 hours\n#### (...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_2352
boxed_number
elementary_math
arithmetic_word_problems
["```python\n# Distance James drives to Canada\ndistance = 360 # miles\n\n# Speed James drives\nspe(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:45035","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, "12", null, null, null, null, null, null, null, null, null, null, null, null ]
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"comparison_type":null,"correct_answer":null,"evaluation_method":"response_processor","extracted_a(...TRUNCATED)
[ [], [], [], [ false ], [], [], [], [], [], [], [], [], [], [], [], [] ]
[ [], [], [], [ "12" ], [], [], [], [], [], [], [], [], [], [], [], [] ]
[[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"12","pattern_used":"answe(...TRUNCATED)
[[],[],[],[{"comparison_type":"mathematical","correct_answer":"7","evaluation_method":"math_equivale(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent(...TRUNCATED)
"The cost of filling a car fuel tank is $45, and this can take you 500 miles before refilling. Mallo(...TRUNCATED)
288
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"If Mallory gammy's house is 2000 miles away and she has to refill the fuel tank every 500 miles, sh(...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_6141
boxed_number
elementary_math
arithmetic_word_problems
["```python\n\n# Cost of filling one fuel tank\nfuel_tank_cost = 45\n\n# Number of tanks needed for (...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:45035","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ null, null, null, null, null, null, null, null, null, "198.0", null, null, null, null, null, null ]
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"comparison_type":null,"correct_answer":null,"evaluation_method":"response_processor","extracted_a(...TRUNCATED)
[ [], [], [], [], [], [], [], [], [], [ false ], [], [], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [ "198.0" ], [], [], [], [], [], [] ]
[[],[],[],[],[],[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"198.0",(...TRUNCATED)
[[],[],[],[],[],[],[],[],[],[{"comparison_type":"mathematical","correct_answer":"288","evaluation_me(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
3