Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
19
273
answer
stringlengths
3
25
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
choices
dict
answer_key
stringclasses
5 values
answer_index
int64
0
4
id
stringlengths
32
34
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
What is the best thing teens can do right after school?
homework
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "smoke", "hang out", "volunteer", "homework", "go to a movie" ] }
D
3
076e84507de0fb03e8f2aa9b1b0187d4
[ "To determine the best thing for teens to do right after school, let's consider each option and its potential benefits:\n\n1. **Smoking**: While smoking might seem appealing due to peer pressure or curiosity, it poses significant health risks and can lead to addiction. This isn't a healthy activity.\n2. **Hang Out*...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nWhat is the best thing teens can do right after school?\n\n# Answer Choices\nA - smoke\nB - hang out\nC - volunteer\nD - homework\nE - go to a movie\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "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, true ]
[ "C", "C", "C", "C", "C", "C", "C", "C", "C", null, "C", "C", "C", "(C)", "Volunteer", "(D) Homework" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 1095, "span_start": 1094, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 831, "span_start": 828, "tot...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, ...
[ [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [], [ false ], [ false ], [ false ], [ false ], [ false ], [ true ] ]
[ [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [], [ "C" ], [ "C" ], [ "C" ], [ "(C)" ], [ "Volunteer" ], [ "(D) Homework" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "C", "pattern_used": "answer tag", "position": 1094, "span_end": 1095, "span_start": 1094, "span_text": "C" } ], [ { "confidence": 1, "extraction_type": "internal", ...
[ [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "leg...
{ "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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
James wanted to eat hamburger. He wanted to do so in order to do what?
satisfy hunger
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "good to eat", "satisfy hunger", "cook one", "taste", "protein" ] }
B
1
7c08fa2e4b29a4772d34999acd8bd1da
[ "Step 1: Determine James' goal.\nJames wants to eat a hamburger.\n\nStep 2: Identify the purpose of eating food.\nThe primary reason for eating food is to satisfy hunger and provide nutrients.\n\nStep 3: Compare James' goal with the options given.\n- A) \"good to eat\" - This doesn't directly address the main purpo...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nJames wanted to eat hamburger. He wanted to do so in order to do what?\n\n# Answer Choices\nA - good to eat\nB - satisfy hunger\nC - cook one\nD - taste\nE - protein\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true ]
[ "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B", "B" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "B", "span_end": 828, "span_start": 825, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "B", "span_end": 992, "span_start": 989, "total...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "l...
[ [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ] ]
[ [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ], [ "B" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "B", "pattern_used": "answer tag", "position": 825, "span_end": 828, "span_start": 825, "span_text": "B" } ], [ { "confidence": 1, "extraction_type": "internal", "or...
[ [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 16, "pass_at_n": 1, "percent_correct": 1, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
Where would you need to use a writing instrument?
classroom
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "pocket", "purse", "classroom", "writer's hand", "stationary" ] }
C
2
d0647d8b8ead25c48e726729c76924b3
[ "To determine where we would need to use a writing instrument, let's consider each option:\n\nA - Pocket: While pockets can hold writing instruments, they don't typically require them.\nB - Purse: Similar to pockets, purses might contain writing instruments but aren't necessary for their use.\nC - Classroom: In a c...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nWhere would you need to use a writing instrument?\n\n# Answer Choices\nA - pocket\nB - purse\nC - classroom\nD - writer's hand\nE - stationary\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, true, true, true, true, false, true, true, true, true, true, true, true, true, true, true ]
[ "C", "C", "C", "C", "C", "E", "C", "C", "C", "C", "C", "C", "C", "C", "C", "C" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 806, "span_start": 803, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 851, "span_start": 848, "total...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "l...
[ [ true ], [ true ], [ true ], [ true ], [ true ], [ false ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ] ]
[ [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "E" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "C", "pattern_used": "answer tag", "position": 803, "span_end": 806, "span_start": 803, "span_text": "C" } ], [ { "confidence": 1, "extraction_type": "internal", "or...
[ [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 15, "pass_at_n": 1, "percent_correct": 0.9375, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
James was dedicated to contemplating things. What did he seek?
enlightenment
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "revelations", "hesitation", "lessons", "new insights", "enlightenment" ] }
E
4
c41b829944815e18e945ba30f2f1ff2d
[ "Step 1: Analyze the given information.\n- James was described as dedicated to contemplating things.\n\nStep 2: Consider the nature of contemplation and its outcomes.\n- Contemplating something typically involves deep thought or reflection.\n- The goal of contemplation often leads to gaining knowledge, understandin...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nJames was dedicated to contemplating things. What did he seek?\n\n# Answer Choices\nA - revelations\nB - hesitation\nC - lessons\nD - new insights\nE - enlightenment\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ false, false, false, true, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "D", "A", "D", "E", "D", "D", "(A) Revelations", "(D)", "C", "D", "A", "(A or D)", "(D)", "D", "D", "(A) Relevations" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "D", "span_end": 1188, "span_start": 1185, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "A", "span_end": 1374, "span_start": 1373, "t...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, ...
[ [ false ], [ false ], [ false ], [ true ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ] ]
[ [ "D" ], [ "A" ], [ "D" ], [ "E" ], [ "D" ], [ "D" ], [ "(A) Revelations" ], [ "(D)" ], [ "C" ], [ "D" ], [ "A" ], [ "(A or D)" ], [ "(D)" ], [ "D" ], [ "D" ], [ "(A) Relevations" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "D", "pattern_used": "answer tag", "position": 1185, "span_end": 1188, "span_start": 1185, "span_text": "D" } ], [ { "confidence": 1, "extraction_type": "internal", ...
[ [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "leg...
{ "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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
He had eaten a lot of asparagus, when he was urinating next he was overcome with what?
unpleasant odors
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "great relief", "easement", "unpleasant odors", "taste of asparagus", "arrest" ] }
C
2
25b93d86095b19df95c038084e1f698a
[ "Step 1: Consider the context of the question.\nThe question mentions that someone has just urinated after eating a lot of asparagus.\n\nStep 2: Recall common reactions to consuming certain foods.\nWhen we eat foods high in fiber or vegetables, it can cause changes in our digestive system and potentially lead to pa...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nHe had eaten a lot of asparagus, when he was urinating next he was overcome with what?\n\n# Answer Choices\nA - great relief\nB - easement\nC - unpleasant odors\nD - taste of asparagus\nE - arrest\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, true, true, true, true, true, true, true, false, true, false, true, true, false, true, true ]
[ "(C)", "C", "C", "C", "C", "C (unpleasant odors)", "C", "C", "A", "C", null, "C", "C", "None of the above", "C", "C" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "(C)", "span_end": 1370, "span_start": 1365, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 1370, "span_start": 1369, ...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": true, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "l...
[ [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ true ], [ false ], [ true ], [], [ true ], [ true ], [ false ], [ true ], [ true ] ]
[ [ "(C)" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C (unpleasant odors)" ], [ "C" ], [ "C" ], [ "A" ], [ "C" ], [], [ "C" ], [ "C" ], [ "None of the above" ], [ "C" ], [ "C" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "(C)", "pattern_used": "answer tag", "position": 1365, "span_end": 1370, "span_start": 1365, "span_text": "(C)" } ], [ { "confidence": 1, "extraction_type": "internal", ...
[ [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy_result": true } ], [ { "evaluation_method": "legacy", "legacy...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 13, "pass_at_n": 1, "percent_correct": 0.8125, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
If I wanted to thank someone for saying I have done a good job, what would I do?
say you're welcome
commonsenseQA
csqa
[ { "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": "Answer the following problem. E...
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "smile", "shake hands", "express gratitude", "say you're welcome", "appreciate compliment" ] }
D
3
f5512f42628808f5c7b23beafa871437
[ "When thanking someone for their compliment, it's important to show appreciation and acknowledge their positive words. Among the given options, expressing gratitude (Option C) directly addresses this need. \n\nTherefore, my final answer is:\n\n<answer>\nC\n</answer>", "To determine the appropriate response when t...
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:41177", "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/Qwen/Qwen2.5-1.5B-Instruct", "prompt": [ { "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": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nIf I wanted to thank someone for saying I have done a good job, what would I do?\n\n# Answer Choices\nA - smile\nB - shake hands\nC - express gratitude\nD - say you're welcome\nE - appreciate compliment\n\nGive your answer in the following format:\n<answer>\n(letter choice)\n</answer>\n\nWhere \"(letter choice)\" is a single capitalized letter option.\n\nLet's think step by step.", "role": "user" } ] }
{ "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 ]
[ "C", "C", "C", "C", "C", "C", "C", "C", "C", "C", "C", "C", "C", "C", "E", "C" ]
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 250, "span_start": 247, "total_spans_found": 1 }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "C", "span_end": 1083, "span_start": 1082, "tot...
[ { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, "legacy_result": false, "reason": null }, { "evaluation_method": "legacy", "extraction_result": null, ...
[ [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ], [ false ] ]
[ [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "C" ], [ "E" ], [ "C" ] ]
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "C", "pattern_used": "answer tag", "position": 247, "span_end": 250, "span_start": 247, "span_text": "C" } ], [ { "confidence": 1, "extraction_type": "internal", "or...
[ [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "legacy_result": false } ], [ { "evaluation_method": "legacy", "leg...
{ "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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 16 }
What happens when friends observe something at the same time?
see like
commonsenseQA
csqa
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
[]
[]
original
{"label":["A","B","C","D","E"],"text":["travel together","borrow money","conspire","visit each other(...TRUNCATED)
E
4
c39e8f18a4e80308e6c1fa8eee745fd1
["When friends observe something at the same time, they are likely to share their observations and o(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:41177","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, false, false, false, false, false, false, false, false, true, false, false ]
[ "C", "C", "C", null, "E", "D", "D", "C", "C", "D", null, "(A)", "C", "E", null, "C" ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"C","span_end":298,"span_start(...TRUNCATED)
[{"evaluation_method":"legacy","extraction_result":null,"legacy_result":false,"reason":null},{"evalu(...TRUNCATED)
[[false],[false],[false],[],[true],[false],[false],[false],[false],[false],[],[false],[false],[true](...TRUNCATED)
[ [ "C" ], [ "C" ], [ "C" ], [], [ "E" ], [ "D" ], [ "D" ], [ "C" ], [ "C" ], [ "D" ], [], [ "(A)" ], [ "C" ], [ "E" ], [], [ "C" ] ]
[[{"confidence":1.0,"extraction_type":"internal","original_span":"C","pattern_used":"answer tag","po(...TRUNCATED)
[[{"evaluation_method":"legacy","legacy_result":false}],[{"evaluation_method":"legacy","legacy_resul(...TRUNCATED)
{"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(...TRUNCATED)
Where can you find a musician that no one is listening to?
studio
commonsenseQA
csqa
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
[]
[]
original
{ "label": [ "A", "B", "C", "D", "E" ], "text": [ "subway station", "symphony", "studio", "orchestra", "stage" ] }
C
2
c7b7d9f4b7c1589fa00c3c221746c985
["To determine where we can find a musician that no one is listening to, let's consider each option:(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:41177","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, false, true, false, false, false, false, false, false, true, false, false, false, false, false, false ]
[ "C", "A", "C", null, "A", null, "A", "A", "E", "C", "E", "stage", "A", null, "A", "E" ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"C","span_end":1262,"span_star(...TRUNCATED)
[{"evaluation_method":"legacy","extraction_result":null,"legacy_result":true,"reason":null},{"evalua(...TRUNCATED)
[[true],[false],[true],[],[false],[],[false],[false],[false],[true],[false],[false],[false],[],[fals(...TRUNCATED)
[ [ "C" ], [ "A" ], [ "C" ], [], [ "A" ], [], [ "A" ], [ "A" ], [ "E" ], [ "C" ], [ "E" ], [ "stage" ], [ "A" ], [], [ "A" ], [ "E" ] ]
[[{"confidence":1.0,"extraction_type":"internal","original_span":"C","pattern_used":"answer tag","po(...TRUNCATED)
[[{"evaluation_method":"legacy","legacy_result":true}],[{"evaluation_method":"legacy","legacy_result(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":3,"pass_at_n":1,"percent(...TRUNCATED)
When someone is not living anymore they?
die
commonsenseQA
csqa
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
[]
[]
original
{"label":["A","B","C","D","E"],"text":["trying to stay happy","seeing","die","experiencing","expire"(...TRUNCATED)
C
2
f453fc718edb62b587d0fac2be4022a3
["To determine what happens when someone is no longer alive, let's consider each option:\n\n1. **Opt(...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:41177","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, true, true, true, false, true, false, true, true, true, false, true, true, true ]
[ "(expire)", "(C)", "C", "C", "C", "C", "E", "C", "E", "C", "C", "C", "E", "C", "C", "C" ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"(expire)","span_end":1384,"sp(...TRUNCATED)
[{"evaluation_method":"legacy","extraction_result":null,"legacy_result":false,"reason":null},{"evalu(...TRUNCATED)
[[false],[true],[true],[true],[true],[true],[false],[true],[false],[true],[true],[true],[false],[tru(...TRUNCATED)
[["(expire)"],["(C)"],["C"],["C"],["C"],["C"],["E"],["C"],["E"],["C"],["C"],["C"],["E"],["C"],["C"],(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"(expire)","pattern_used":"answer t(...TRUNCATED)
[[{"evaluation_method":"legacy","legacy_result":false}],[{"evaluation_method":"legacy","legacy_resul(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":12,"pass_at_n":1,"percen(...TRUNCATED)
"The tickets were supposed to arrive by 1AM, but Sally had been standing in queue for the concert si(...TRUNCATED)
delays
commonsenseQA
csqa
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
[]
[]
original
{"label":["A","B","C","D","E"],"text":["delays","frustration","sprinting","moving forward","being an(...TRUNCATED)
A
0
7dc95daa5daa899ba0817d4cee09d313
["When considering why the line hadn't moved after Sally had been waiting from midnight until 2 AM, (...TRUNCATED)
[ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:41177","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct", "n_responses": 16 }
[ true, true, true, false, true, false, true, true, true, false, false, true, true, true, true, true ]
[ "A", "A (delays)", "A", "B", "A", "D", "A", "A", "A", "B", "E", "A", "A", "A", "A", "A" ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"A","span_end":1109,"span_star(...TRUNCATED)
[{"evaluation_method":"legacy","extraction_result":null,"legacy_result":true,"reason":null},{"evalua(...TRUNCATED)
[[true],[true],[true],[false],[true],[false],[true],[true],[true],[false],[false],[true],[true],[tru(...TRUNCATED)
[["A"],["A (delays)"],["A"],["B"],["A"],["D"],["A"],["A"],["A"],["B"],["E"],["A"],["A"],["A"],["A"],(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"A","pattern_used":"answer tag","po(...TRUNCATED)
[[{"evaluation_method":"legacy","legacy_result":true}],[{"evaluation_method":"legacy","legacy_result(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":12,"pass_at_n":1,"percen(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
4