Datasets:

Modalities:
Text
Formats:
parquet
Libraries:
Datasets
pandas
Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
64
859
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
57
1.2k
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
Amaya scored 20 marks fewer in Maths than she scored in Arts. She also got 10 marks more in Social Studies than she got in Music. If she scored 70 in Music and scored 1/10 less in Maths, what's the total number of marks she scored in all the subjects?
296
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
The total marks Amaya scored more in Music than in Maths is 1/10 * 70 = <<1/10*70=7>>7 marks. So the total marks she scored in Maths is 70 - 7 = <<70-7=63>>63 marks. If she scored 20 marks fewer in Maths than in Arts, then he scored 63 + 20 = <<63+20=83>>83 in Arts. If she scored 10 marks more in Social Studies than in...
math
numeric_equivalence
gsm8k
main
gsm8k_5579
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Given values\nmusic_score = 70\n\n# Calculate the score for Arts\narts_score = music_score + 20\n\n# Calculate the score for Social Studies\nsocial_studies_score = music_score + 10\n\n# Calculate the score for Maths\nmaths_score = music_score - (music_score * 1/10)\n\n# Calculate the total score\ntota...
[ 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, "(94)", 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": ...
[ [], [], [], [], [], [], [], [], [], [ false ], [], [], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [ "(94)" ], [], [], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "(94)", "pattern_used": "answer tag", "position": 619, "span_end": 625, "span_start": 619, "span_text": "(94)" } ], [], [], [], ...
[ [], [], [], [], [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "296", "evaluation_method": "math_equivalence", "extracted_answer": "(94)", "is_equivalent": false } ], [], [], [], [], [], [] ]
{ "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, ...
Luis is driving 80 miles in 2 hours. How far will he go in 15 minutes?
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
Luis drives 80/2 = <<80/2=40>>40 miles in 1 hour. Since there are 60 minutes in 1 hour, then he drives 40/60 = 2/3 of a mile in 1 minute. So in 15 minutes, he will go 2/3 x 15 = <<2/3*15=10>>10 miles far. #### 10
math
numeric_equivalence
gsm8k
main
gsm8k_3952
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Luis's speed in miles per hour\nspeed = 80 / 2\n\n# Time in hours for which we need to calculate distance\ntime_hours = 15 / 60\n\n# Distance formula: distance = speed * time\ndistance = speed * time_hours\n\ndistance\n```", "```python\n# Luis drives 80 miles in 2 hours.\n# We need to find how far h...
[ 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, true, false, false, false, false, false, false, false, false, false, false ]
[ null, null, "30.0", null, "40", "(10)", null, null, null, null, null, "32", 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": ...
[ [], [], [ false ], [], [ false ], [ true ], [], [], [], [], [], [ false ], [], [], [], [] ]
[ [], [], [ "30.0" ], [], [ "40" ], [ "(10)" ], [], [], [], [], [], [ "32" ], [], [], [], [] ]
[ [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "30.0", "pattern_used": "answer tag", "position": 286, "span_end": 290, "span_start": 286, "span_text": "30.0" } ], [], [ { "confidence": 1, "extraction_type...
[ [], [], [ { "comparison_type": "mathematical", "correct_answer": "10", "evaluation_method": "math_equivalence", "extracted_answer": "30.0", "is_equivalent": false } ], [], [ { "comparison_type": "mathematical", "correct_answer": "10", "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, ...
Hannah fills her kids' stockings with 4 candy canes, 2 beanie babies and 1 book. If she has 3 kids, how many stocking stuffers does she buy total?
21
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 total number of stocking stuffers one kid gets: 4 candy canes + 2 beanie babies + 1 book = <<4+2+1=7>>7 stocking stuffers Then multiply the number of stocking stuffers per kid by the number of kids to find the total number: 7 stocking stuffers/kid * 3 kids = <<7*3=21>>21 stocking stuffers #### 21
math
numeric_equivalence
gsm8k
main
gsm8k_4301
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Number of items per stocking\ncandy_canes_per_stocking = 4\nbeanie_babies_per_stocking = 2\nbooks_per_stocking = 1\n\n# Number of children\nnum_children = 3\n\n# Calculate total items for one child\ntotal_items_per_child = candy_canes_per_stocking + beanie_babies_per_stocking + books_per_stocking\n\n#...
[ 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 ]
[ "19", null, null, null, null, null, null, null, null, null, null, null, null, null, null, null ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "19", "span_end": 508, "span_start": 506, "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": "21", "evaluation_method": "math_equivalence", "extracted_answer": "19", "extraction_result": null, "is_equivalent": false, "reason": null }, { "comparison_type": null, "correct_answer": null, "evaluation_method": "re...
[ [ false ], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [] ]
[ [ "19" ], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "19", "pattern_used": "answer tag", "position": 506, "span_end": 508, "span_start": 506, "span_text": "19" } ], [], [], [], [], [], [], [], [], [], [], [], [], [],...
[ [ { "comparison_type": "mathematical", "correct_answer": "21", "evaluation_method": "math_equivalence", "extracted_answer": "19", "is_equivalent": false } ], [], [], [], [], [], [], [], [], [], [], [], [], [], [], [] ]
{ "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, ...
Georgie needs 3 avocados to make her grandmother's guacamole recipe. If she already had 5 avocados and her sister buys another 4 avocados, how many servings of guacamole can Georgie make?
3
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
Altogether, Georgie has 5 + 4 = <<5+4=9>>9 avocados. She can make 9/3 = <<9/3=3>>3 servings of guacamole. #### 3
math
numeric_equivalence
gsm8k
main
gsm8k_703
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n\n# Initial number of avocados Georgie has\ninitial_avocados = 5\n\n# Number of avocados Georgie's sister buys\nsister_buys = 4\n\n# Total number of avocados after buying more from sister\ntotal_avocados = initial_avocados + sister_buys\n\n# Avocados needed per serving of guacamole\navocados_per_serving...
[ 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, "6", 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": ...
[ [], [], [], [ false ], [], [], [], [], [], [], [], [], [], [], [], [] ]
[ [], [], [], [ "6" ], [], [], [], [], [], [], [], [], [], [], [], [] ]
[ [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "6", "pattern_used": "answer tag", "position": 956, "span_end": 959, "span_start": 956, "span_text": "6" } ], [], [], [], [], [], [], [], [], [], [], ...
[ [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "3", "evaluation_method": "math_equivalence", "extracted_answer": "6", "is_equivalent": false } ], [], [], [], [], [], [], [], [], [], [], [], [] ]
{ "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, ...
Kenny plans to mow lawns all summer, and then use the profits to buy video-games and books. He charges $15 per lawn. The video-games are $45 each. The books are $5 each. At the end of the summer he has mowed 35 lawns. There are 5 video-games he really wants, and then he will use the rest for books. How many books can h...
60
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
Kenny earns $525 because 35 x 15 = <<35*15=525>>525 He spends $225 on video games because 5 x 45 = <<5*45=225>>225 He has $300 left because 525 - 225 = <<525-225=300>>300 He can buy 60 books because 300 / 5 = <<300/5=60>>60 #### 60
math
numeric_equivalence
gsm8k
main
gsm8k_5266
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n\n# Constants\nkenny_charge_per_lawn = 15\nnum_video_games = 5\nnum_books_needed = 0 # We need to find how many books Kenny can buy first\n\n# Calculations\ntotal_income_from_lawns = kenny_charge_per_lawn * num_lawns_mowed\nprofit_after_lawns = total_income_from_lawns - (video_game_cost * num_video_gam...
[ 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, true, false, false, false, false, false ]
[ null, null, null, null, null, null, null, null, null, null, "60", 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": ...
[ [], [], [], [], [], [], [], [], [], [], [ true ], [], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [], [ "60" ], [], [], [], [], [] ]
[ [], [], [], [], [], [], [], [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "60", "pattern_used": "answer tag", "position": 1086, "span_end": 1088, "span_start": 1086, "span_text": "60" } ], [], [], ...
[ [], [], [], [], [], [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "60", "evaluation_method": "math_equivalence", "extracted_answer": "60", "is_equivalent": true } ], [], [], [], [], [] ]
{ "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, ...
In 10 years, Cornelia will be three times as old as Kilee. If Kilee is currently 20 years old, how old is Cornelia now?
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
In 10 years, Kilee will be 20 years + 10 years = 30 years. In ten years, Cornelia will be 3 * 30 years = <<3*30=90>>90 years old. Cornelia is currently 90 years - 10 years = <<90-10=80>>80 years old #### 80
math
numeric_equivalence
gsm8k
main
gsm8k_5685
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Given data\nkilee_current_age = 20\n\n# In 10 years, Cornelia will be three times as old as Kilee\ncornelia_future_age = kilee_current_age * 3 + 10\n\n# To find Cornelia's current age, we subtract 10 from her future age\ncornelia_current_age = cornelia_future_age - 10\n\ncornelia_current_age\n```", ...
[ 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, "(70)", null, null, null, null, "60", 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": ...
[ [], [], [], [ false ], [], [], [], [], [ false ], [], [], [], [], [], [], [] ]
[ [], [], [], [ "(70)" ], [], [], [], [], [ "60" ], [], [], [], [], [], [], [] ]
[ [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "(70)", "pattern_used": "answer tag", "position": 323, "span_end": 329, "span_start": 323, "span_text": "(70)" } ], [], [], [], [], [ { "confidence": 1...
[ [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "80", "evaluation_method": "math_equivalence", "extracted_answer": "(70)", "is_equivalent": false } ], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answer":...
{ "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, ...
Nicky is trading baseball cards with Jill. If Nicky trades two cards worth $8 each for 1 card worth $21, how many dollars of profit does he make?
5
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 total cost of the two $8 cards: $8/card * 2 cards = $<<8*2=16>>16 Then subtract the cost of the cards Nicky gave away from the cost of the card he received to find his profit: $21 - $16 = $<<21-16=5>>5 #### 5
math
numeric_equivalence
gsm8k
main
gsm8k_2663
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n# Define the values of the traded cards and the value of the received card\nvalue_of_two_traded_cards = 8 * 2\nvalue_of_received_card = 21\n\n# Calculate the profit\nprofit = value_of_received_card - value_of_two_traded_cards\n\nprint(profit)\n```", "```python\n# Initial values\nnicky_cards_worth_8 = ...
[ 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, "47", null, null, null, null, null, null, null, "0", 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": 1, "original_span": "47", "span_end": 439, "span_start": 437, ...
[ { "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": "mathematical", "correct...
[ [], [ false ], [], [], [], [], [], [], [], [ false ], [], [], [], [], [], [] ]
[ [], [ "47" ], [], [], [], [], [], [], [], [ "0" ], [], [], [], [], [], [] ]
[ [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "47", "pattern_used": "answer tag", "position": 437, "span_end": 439, "span_start": 437, "span_text": "47" } ], [], [], [], [], [], [], [], [ { "confidence":...
[ [], [ { "comparison_type": "mathematical", "correct_answer": "5", "evaluation_method": "math_equivalence", "extracted_answer": "47", "is_equivalent": false } ], [], [], [], [], [], [], [], [ { "comparison_type": "mathematical", "correct_answe...
{ "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, ...
Five dozens of people are attending your family reunion. Your family was assigned to bring the cans of soda. Each box of soda contains 10 cans and costs $2 per box. It was assumed that each person can consume 2 cans of soda. If you are six in the family and agreed to pay equally for the cost, how much will each of your...
4
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
Five dozens of people is equal to 5 x 12 = <<5*12=60>>60. 60 x 2 = <<60*2=120>>120 cans of soda are needed. So, this means 120/10 = <<120/10=12>>12 boxes of soda must be purchased. Thus, it will amount to $2 x 12 = $<<24=24>>24. Therefore, each family member will pay $24/6 = $<<24/6=4>>4. #### 4
math
numeric_equivalence
gsm8k
main
gsm8k_3956
boxed_number
elementary_math
arithmetic_word_problems
[ "```python\n\n# Step 1: Calculate total number of cans needed\ntotal_people = 5 * 12 # Five dozen people\ncans_per_person = 2 # Each person consumes 2 cans\ntotal_cans_needed = total_people * cans_per_person\n\n# Step 2: Calculate number of boxes required\ncans_per_box = 10 # Each box contains 10 cans\nbox...
[ 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, "(8.0)", null, null, null, null, null, null, null, null, null, null, null, "9.33" ]
[ { "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 ] ]
[ [], [], [], [ "(8.0)" ], [], [], [], [], [], [], [], [], [], [], [], [ "9.33" ] ]
[ [], [], [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "(8.0)", "pattern_used": "answer tag", "position": 664, "span_end": 671, "span_start": 664, "span_text": "(8.0)" } ], [], [], [], [], [], [], [], [], [],...
[ [], [], [], [ { "comparison_type": "mathematical", "correct_answer": "4", "evaluation_method": "math_equivalence", "extracted_answer": "(8.0)", "is_equivalent": false } ], [], [], [], [], [], [], [], [], [], [], [], [ { "comparison_type...
{ "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, ...
"Amalia can read 4 pages of her book in 2 minutes. How many minutes will it take her to read 18 page(...TRUNCATED)
9
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"Amalia can read 1 page in 2/4 = 0.5 minutes.\nHence, she can read 18 pages in 18 x 0.5 minutes = <<(...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_4861
boxed_number
elementary_math
arithmetic_word_problems
["```python\n# Given data\npages_read_per_2_minutes = 4\ntotal_pages_to_read = 18\n\n# Calculate tim(...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, true, true, false, false, false, true, true, false, false, false, true, false, false, false, false ]
[ null, "9.0", "9", null, null, null, "9.0", "9", null, "(36)", null, "9.0", null, null, "6", 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)
[ [], [ true ], [ true ], [], [], [], [ true ], [ true ], [], [ false ], [], [ true ], [], [], [ false ], [] ]
[ [], [ "9.0" ], [ "9" ], [], [], [], [ "9.0" ], [ "9" ], [], [ "(36)" ], [], [ "9.0" ], [], [], [ "6" ], [] ]
[[],[{"confidence":1.0,"extraction_type":"internal","original_span":"9.0","pattern_used":"answer tag(...TRUNCATED)
[[],[{"comparison_type":"mathematical","correct_answer":"9","evaluation_method":"math_equivalence","(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":5,"pass_at_n":1,"percent(...TRUNCATED)
"Jaylen’s dog eats 1 cup of dog food in the morning and 1 cup of dog food in the evening. If she (...TRUNCATED)
16
gsm8k
gsm8k
[{"content":"You like to solve problems by thinking in python code. Write a python script that would(...TRUNCATED)
[]
[]
python_prog
"Every day, Jaylen’s dog eats 1 x 2 = <<1*2=2>>2 cups of dog food.\nThe bag will feed her dog for (...TRUNCATED)
math
numeric_equivalence
gsm8k
main
gsm8k_3281
boxed_number
elementary_math
arithmetic_word_problems
["```python\n\n# Define the variables\ncups_per_day = 1 + 1 # Morning and evening meals\ntotal_cups(...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, true, true, false, false, true, false, false, false, false, true, false, false ]
[ null, null, null, null, "16", "16", "<number_of_days>", null, "16", null, null, null, null, "16", 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)
[ [], [], [], [], [ true ], [ true ], [ false ], [], [ true ], [], [], [], [], [ true ], [], [] ]
[ [], [], [], [], [ "16" ], [ "16" ], [ "<number_of_days>" ], [], [ "16" ], [], [], [], [], [ "16" ], [], [] ]
[[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"16","pattern_used":"an(...TRUNCATED)
[[],[],[],[],[{"comparison_type":"mathematical","correct_answer":"16","evaluation_method":"math_equi(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
8