Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
7
989
answer
stringlengths
0
28
task_config
stringclasses
14 values
task_source
stringclasses
6 values
prompt
listlengths
1
1
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
all_other_columns
stringlengths
90
1.36k
original_split
stringclasses
1 value
acronym
stringclasses
341 values
answer_index
int64
0
4
answer_key
stringclasses
5 values
choices
stringlengths
4
148
difficulty
stringclasses
1 value
domain
stringclasses
1 value
evaluation_type
stringclasses
1 value
expected_answer_format
stringclasses
1 value
formed_acronym
stringclasses
341 values
id
stringlengths
7
34
length
int64
4
8
letters
stringclasses
600 values
metadata
stringlengths
2
152
original_answer
stringlengths
48
1.07k
source
stringclasses
601 values
task_type
stringclasses
1 value
variant
stringclasses
1 value
word_count
int64
4
8
words
listlengths
4
8
model_responses__best_of_n_atags
listlengths
4
4
model_responses__best_of_n_atags__finish_reason_length_flags
listlengths
4
4
model_responses__best_of_n_atags__length_partial_responses
listlengths
4
4
prompt__best_of_n_atags__metadata
stringlengths
784
1.57k
model_responses__best_of_n_atags__metadata
stringclasses
1 value
eval_date
stringdate
2025-09-24 00:00:00
2025-09-24 00:00:00
model_responses__best_of_n_atags__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__eval_extraction_metadata
stringlengths
120
3.08k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
3.09k
model_responses__best_of_n_atags__internal_answers__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata
stringlengths
192
15.2k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
70
8.25k
model_responses__best_of_n_atags__metrics
dict
question_idx
int64
0
1.32k
response_idx
int64
0
3
original_response_idx_in_16
int64
0
3
original_response
stringlengths
279
18.6k
budget_forced_continuations
dict
model_responses__budget_forced
listlengths
2
2
model_responses__budget_forced__eval_is_correct
listlengths
2
2
model_responses__budget_forced__eval_extracted_answers
listlengths
2
2
model_responses__budget_forced__eval_extraction_metadata
stringlengths
60
2.79k
model_responses__budget_forced__eval_evaluation_metadata
stringlengths
112
2.85k
model_responses__budget_forced__internal_answers__eval_is_correct
listlengths
2
2
model_responses__budget_forced__internal_answers__eval_extracted_answers
listlengths
2
2
model_responses__budget_forced__internal_answers__eval_extraction_metadata
stringlengths
184
221k
model_responses__budget_forced__internal_answers__eval_evaluation_metadata
stringlengths
62
157k
model_responses__budget_forced__metrics
dict
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>. # Problem Using the numbers in the list [29, 23, 31], create an equation that equals 698. You can use basic arithmetic operations (+, -, *, /) and each number can o...
23*29 + 31
countdown_3arg
countdown
[ { "content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [29, 23, 31], create an equation that equals 698. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5115, \"numbers\": [29, 23, 31], \"target\": 698, \"expression\": \"23*29 + 31\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5115, "numbers": [29, 23, 31], "target": 698, "expression": "23*29 + 31"}
null
null
null
null
null
null
[ "<think>\nI have the numbers [29, 23, 31] and need to make 698 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.\n\nFirst, I should consider what operations might get me close to 698. Since 698 is fairly large, multiplication might be involved...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://127.0.0.1:41869/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": {"chat_template_applied": true, "max_tokens": 4096, "n": 4, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8}, "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_on...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only", "n_responses": 4}
2025-09-24
[ false, false, false, false ]
[ "(29 × 23) + 31", "(your answer)", "(29 × 23) + 31", "\\(29 \\times 23 + 31\\)" ]
[{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 5654, "span_end": 5670, "original_span": "(29 \u00d7 23) + 31"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2764, "span_end": 2777, "original_span": "(your answer)"}, {"ext...
[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(29 \u00d7 23) + 31", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_b...
[ [ false, false, false ], [ false ], [ false ], [ false ] ]
[ [ "(your answer)", "(your answer)", "(29 × 23) + 31" ], [ "(your answer)" ], [ "(29 × 23) + 31" ], [ "\\(29 \\times 23 + 31\\)" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2875, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2875, "span_end": 2888, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 4582, "span_text": "(your answer)", "extraction_type":...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block"...
{ "flips_by": [ 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 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, 0, ...
108
1
1
<think> I have the numbers [29, 23, 31] and need to make 698 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once. First, I should consider what operations might get me close to 698. Since 698 is a fairly large number, multiplication might be involve...
{ "response": "<think>\nI have the numbers [29, 23, 31] and need to make 698 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nFirst, I should consider what operations might get me close to 698. Since 698 is a fairly large number, multiplicat...
[ "<think>\nI have the numbers [29, 23, 31] and need to make 698 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nFirst, I should consider what operations might get me close to 698. Since 698 is a fairly large number, multiplication might be...
[ false, false ]
[ "(your answer)", "(29 × 23) + 31" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2764, "span_end": 2777, "original_span": "(your answer)"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 6504, "span_end": 6520, "original_span": "(29 \u00d7 23) + 31"}]
[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(29 \u00d7 23) + 31", "final_answer": null}]
[ [ false ], [ false, false, false, false ] ]
[ [ "(your answer)" ], [ "(your answer)", "(29 × 23) + 31", "(29 × 23) + 31", "(29 × 23) + 31" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2764, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2764, "span_end": 2777, "original_span": "(your answer)"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 2764, "span_text": "(your answer)", "extraction_type...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}], [{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_bloc...
{ "flips_by": [ 0, 0 ], "flips_total": 0, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0 ], "best_of_n": [ 0, 0 ], "reflect_close": [ 0, 0 ], "reflect_open": [ 0, 0 ]...
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
40 - 9 + 97
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 6049, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 6049, \"numbers\": [40, 9, 97], \"target\": 1(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [40, 9, 97] and need to make an equation that equals 128 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, false, true ]
["40 + 97 - 9","(97 + 40) - 9","Step 1: 97 * 9 = 873 \nStep 2: 873 - 745 = 128","Step 1: 97 - 9 = 8(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"40 + 97 - 9\", \"final_answer\": 128.0(...TRUNCATED)
[ [ false, true, true, true ], [ true ], [ false, false ], [ true ] ]
[["(your answer)","40 + 97 - 9","Step 1: 40 + 97 = 137\nStep 2: 137 - 9 = 128","40 + 97 - 9"],["(97 (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6783, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
978
0
0
"<think>\nFirst, I have the numbers [40, 9, 97] and need to make an equation that equals 128 using b(...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers [40, 9, 97] and need to make an equation that equals(...TRUNCATED)
["<think>\nFirst, I have the numbers [40, 9, 97] and need to make an equation that equals 128 using (...TRUNCATED)
[ true, true ]
[ "40 + 97 - 9", "40 + 97 - 9" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"40 + 97 - 9\", \"final_answer\": 128.0(...TRUNCATED)
[ [ false, true, true, true ], [ false, true, true, true, true, true, true ] ]
[["(your answer)","40 + 97 - 9","Step 1: 40 + 97 = 137\nStep 2: 137 - 9 = 128","40 + 97 - 9"],["(you(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6783, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
26*9 + 77
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5881, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5881, \"numbers\": [77, 26, 9], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [77, 26, 9] and need to make 311 using basic arithmetic operations: ad(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, false, false, false ]
[ "Step 1: 26 * 9 = 234 \nStep 2: 234 + 77 = 311", "(26 × 9) + 77", "9 \\times 26 + 77", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 26 * 9 = 234 \\nStep 2: 234 +(...TRUNCATED)
[ [ true ], [ true, false, false ], [ false, false ], [] ]
[["Step 1: 26 * 9 = 234 \nStep 2: 234 + 77 = 311"],["(26 * 9) + 77","(your answer)","(26 × 9) + 77(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4145, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 26 * 9 = 234 \\nStep 2: 234 (...TRUNCATED)
{"flips_by":[0,1,0,0],"flips_total":1,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
819
0
0
"<think>\nI have the numbers [77, 26, 9] and need to make 311 using basic arithmetic operations: add(...TRUNCATED)
{"response":"<think>\nI have the numbers [77, 26, 9] and need to make 311 using basic arithmetic ope(...TRUNCATED)
["<think>\nI have the numbers [77, 26, 9] and need to make 311 using basic arithmetic operations: ad(...TRUNCATED)
[ true, false ]
[ "Step 1: 26 * 9 = 234 \nStep 2: 234 + 77 = 311", "(26 × 9) + 77" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 26 * 9 = 234 \\nStep 2: 234 +(...TRUNCATED)
[ [ true ], [ false, false ] ]
[ [ "Step 1: 26 * 9 = 234 \nStep 2: 234 + 77 = 311" ], [ "(26 × 9) + 77", "(26 × 9) + 77" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4145, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 26 * 9 = 234 \\nStep 2: 234 (...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.5,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
70 + 97 - 41
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5799, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5799, \"numbers\": [70, 97, 41], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [70, 97, 41] and need to make an equation that equals 126 using basic (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, false ]
[ "Step 1: 97 + 70 = 167\nStep 2: 167 - 41 = 126", "(97 - 41) + 70", "(70 + 97) - 41 = 126", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 97 + 70 = 167\\nStep 2: 167 - (...TRUNCATED)
[ [ true, false, true ], [ true, false, true, true ], [ true, true ], [] ]
[["Step 1: 97 + 70 = 167 \nStep 2: 167 - 41 = 126","(your answer)","Step 1: 97 + 70 = 167\nStep 2: (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5910, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 97 + 70 = 167 \\nStep 2: 167(...TRUNCATED)
{"flips_by":[1,1,0,0],"flips_total":2,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
745
1
1
"<think>\nFirst, I have the numbers: 70, 97, and 41. I need to use each exactly once with basic arit(...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers: 70, 97, and 41. I need to use each exactly once wit(...TRUNCATED)
["<think>\nFirst, I have the numbers: 70, 97, and 41. I need to use each exactly once with basic ari(...TRUNCATED)
[ true, true ]
[ "(97 - 41) + 70", "(97 - 41) + 70" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(97 - 41) + 70\", \"final_answer\": 12(...TRUNCATED)
[ [ true, false, true, true ], [ true, false, true, true, true, true, true, true ] ]
[["(97 - 41) + 70","(your answer)","Step 1: 97 - 41 = 56\nStep 2: 56 + 70 = 126","(97 - 41) + 70"],[(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4801, \"span_text\": \"(97 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(97 - 41) + 70\", \"final_answer\": 1(...TRUNCATED)
{"flips_by":[1,1],"flips_total":2,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
78 + 11 + 15
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5253, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5253, \"numbers\": [11, 78, 15], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [11, 78, 15] and I need to use them to make 104 using addition,(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, true ]
["(15 + 11) + 78","11 + 78 + 15","Step 1: 11 + 78 = 89 \nStep 2: 89 + 15 = 104","Step 1: 78 + 15 = (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(15 + 11) + 78\", \"final_answer\": 10(...TRUNCATED)
[ [ true, true ], [ true, true ], [ false, true, true ], [ true ] ]
[["(15 + 11) + 78","(15 + 11) + 78"],["11 + 78 + 15 = 104","11 + 78 + 15"],["(your answer)","Step 1:(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4071, \"span_text\": \"(15 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(15 + 11) + 78\", \"final_answer\": 1(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
239
2
2
"<think>\nFirst, I have the numbers [11, 78, 15] and need to make 104 using basic arithmetic operati(...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers [11, 78, 15] and need to make 104 using basic arithm(...TRUNCATED)
["<think>\nFirst, I have the numbers [11, 78, 15] and need to make 104 using basic arithmetic operat(...TRUNCATED)
[ true, true ]
[ "Step 1: 11 + 78 = 89 \nStep 2: 89 + 15 = 104", "Step 1: 11 + 78 = 89 \nStep 2: 89 + 15 = 104" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 11 + 78 = 89 \\nStep 2: 89 + (...TRUNCATED)
[ [ false, true, true ], [ false, true, true, true, true ] ]
[["(your answer)","Step 1: 11 + 78 = 89 \nStep 2: 89 + 15 = 104","Step 1: 11 + 78 = 89 \nStep 2: 8(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5233, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
40*25 - 15
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5339, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5339, \"numbers\": [25, 15, 40], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [25, 15, 40] and need to make 985 using basic arithmetic operations: a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, false, true, true ]
["(40 * 25) - 15","(25 × 40) − 15","Step 1: 25 * 40 = 1000 \nStep 2: 1000 - 15 = 985","Step 1: 2(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(40 * 25) - 15\", \"final_answer\": 98(...TRUNCATED)
[ [ true, true ], [ false ], [ false, true ], [ true, true ] ]
[["(40 * 25) - 15","(40 * 25) - 15"],["(25 × 40) − 15"],["(your answer)","Step 1: 25 * 40 = 1000 (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3132, \"span_text\": \"(40 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(40 * 25) - 15\", \"final_answer\": 9(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
321
2
2
"<think>\nI have the numbers [25, 15, 40] and need to make an equation that equals 985 using additio(...TRUNCATED)
{"response":"<think>\nI have the numbers [25, 15, 40] and need to make an equation that equals 985 u(...TRUNCATED)
["<think>\nI have the numbers [25, 15, 40] and need to make an equation that equals 985 using additi(...TRUNCATED)
[ true, false ]
[ "Step 1: 25 * 40 = 1000 \nStep 2: 1000 - 15 = 985", "(25 × 40) − 15" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 25 * 40 = 1000 \\nStep 2: 100(...TRUNCATED)
[ [ false, true ], [ false, false, false ] ]
[["(your answer)","Step 1: 25 * 40 = 1000 \nStep 2: 1000 - 15 = 985"],["(your answer)","(25 × 40) (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3227, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.5,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
38 - 7 + 88
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5951, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5951, \"numbers\": [88, 7, 38], \"target\": 1(...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [88, 7, 38] and need to make an equation that equals 119 using basic a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, false ]
[ "(88 - 7) + 38", "Step 1: 88 - 7 = 81\nStep 2: 81 + 38 = 119", "(88 - 7) + 38 = 119", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(88 - 7) + 38\", \"final_answer\": 119(...TRUNCATED)
[ [ true ], [ true, true ], [ true, false, true ], [] ]
[["(88 - 7) + 38"],["Step 1: 88 - 7 = 81\nStep 2: 81 + 38 = 119","Step 1: 88 - 7 = 81\nStep 2: 81 + (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5449, \"span_text\": \"(88 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(88 - 7) + 38\", \"final_answer\": 11(...TRUNCATED)
{"flips_by":[0,0,1,0],"flips_total":1,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
881
0
0
"<think>\nI have the numbers [88, 7, 38] and need to make an equation that equals 119 using basic ar(...TRUNCATED)
{"response":"<think>\nI have the numbers [88, 7, 38] and need to make an equation that equals 119 us(...TRUNCATED)
["<think>\nI have the numbers [88, 7, 38] and need to make an equation that equals 119 using basic a(...TRUNCATED)
[ true, true ]
[ "(88 - 7) + 38", "(88 - 7) + 38" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(88 - 7) + 38\", \"final_answer\": 119(...TRUNCATED)
[ [ true ], [ false, true, true, true ] ]
[ [ "(88 - 7) + 38" ], [ "(your answer)", "(88 - 7) + 38", "(88 - 7) + 38", "(88 - 7) + 38" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5449, \"span_text\": \"(88 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(88 - 7) + 38\", \"final_answer\": 11(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
93 + 96 - 66
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5057, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5057, \"numbers\": [93, 96, 66], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [93, 96, 66] and need to make 123 using basic arithmetic operations: a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, true ]
["Step 1: 93 + 96 = 189 \nStep 2: 189 - 66 = 123","Step 1: 93 + 96 = 189 \nStep 2: 189 - 66 = 123"(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 96 = 189 \\nStep 2: 189 (...TRUNCATED)
[ [ true, true, true ], [ false, true ], [ false, true ], [ true, true ] ]
[["Step 1: 93 + 96 = 189\nStep 2: 189 - 66 = 123","(93 + 96) - 66 = 123","Step 1: 93 + 96 = 189 \nS(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3371, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 96 = 189\\nStep 2: 189 -(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
52
0
0
"<think>\nI have the numbers [93, 96, 66] and need to make 123 using basic arithmetic operations: ad(...TRUNCATED)
{"response":"<think>\nI have the numbers [93, 96, 66] and need to make 123 using basic arithmetic op(...TRUNCATED)
["<think>\nI have the numbers [93, 96, 66] and need to make 123 using basic arithmetic operations: a(...TRUNCATED)
[ true, true ]
[ "Step 1: 93 + 96 = 189 \nStep 2: 189 - 66 = 123", "Step 1: 93 + 96 = 189\nStep 2: 189 - 66 = 123" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 96 = 189 \\nStep 2: 189 (...TRUNCATED)
[ [ true, true, true ], [ true, true, true, true, true ] ]
[["Step 1: 93 + 96 = 189\nStep 2: 189 - 66 = 123","(93 + 96) - 66 = 123","Step 1: 93 + 96 = 189 \nS(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3371, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 96 = 189\\nStep 2: 189 -(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
68 + 82 + 56
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5690, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5690, \"numbers\": [56, 82, 68], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [56, 82, 68] and need to make 206 using basic arithmetic operations: a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, true ]
[ "56 + 82 + 68 = 206", "56 + 82 + 68", "56 + 82 + 68 = 206", "(56 + 82) + 68 = 206" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"56 + 82 + 68 = 206\", \"final_answer\"(...TRUNCATED)
[ [ false, true, true ], [ false, true ], [ false, true, true, true ], [ false, true, true ] ]
[["(your answer)","56 + 82 + 68 = 206","56 + 82 + 68 = 206"],["(your answer)","56 + 82 + 68"],["(you(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3601, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
644
2
2
"<think>\nI have the numbers [56, 82, 68] and need to make an equation that equals 206 using basic a(...TRUNCATED)
{"response":"<think>\nI have the numbers [56, 82, 68] and need to make an equation that equals 206 u(...TRUNCATED)
["<think>\nI have the numbers [56, 82, 68] and need to make an equation that equals 206 using basic (...TRUNCATED)
[ true, true ]
[ "56 + 82 + 68 = 206", "56 + 82 + 68" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"56 + 82 + 68 = 206\", \"final_answer\"(...TRUNCATED)
[ [ false, true, true, true ], [ false, true, true, true, false, false, true, true, true ] ]
[["(your answer)","56 + 82 + 68 = 206","Step 1: 56 + 82 = 138\nStep 2: 138 + 68 = 206","56 + 82 + 68(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2704, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,1],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
33 - 12 + 94
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5157, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5157, \"numbers\": [33, 94, 12], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [33, 94, 12] and I need to make an equation that equals 115 using basi(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
2025-09-24
[ true, true, true, true ]
["94 + 33 - 12","Step 1: 94 + 33 = 127 \nStep 2: 127 - 12 = 115","94 + (33 - 12)","Step 1: 94 + 33 (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"94 + 33 - 12\", \"final_answer\": 115.(...TRUNCATED)
[ [ true, false, true ], [ true, false, false, true ], [ true ], [ true ] ]
[["94 + 33 - 12 = 115","(your answer)","94 + 33 - 12"],["Step 1: 94 + 33 = 127 \nStep 2: 127 - 12 =(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6640, \"span_text\": \"94 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"94 + 33 - 12 = 115\", \"final_answer\(...TRUNCATED)
{"flips_by":[1,1,0,0],"flips_total":2,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
149
3
3
"<think>\nI have the numbers [33, 94, 12] and I need to make an equation that equals 115 using basic(...TRUNCATED)
{"response":"<think>\nI have the numbers [33, 94, 12] and I need to make an equation that equals 115(...TRUNCATED)
["<think>\nI have the numbers [33, 94, 12] and I need to make an equation that equals 115 using basi(...TRUNCATED)
[ true, true ]
[ "Step 1: 94 + 33 = 127 \nStep 2: 127 - 12 = 115", "(94 + 33) - 12" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 94 + 33 = 127 \\nStep 2: 127 (...TRUNCATED)
[ [ true ], [ true, true, true, true ] ]
[["Step 1: 94 + 33 = 127 \nStep 2: 127 - 12 = 115"],["Step 1: 94 + 33 = 127 \nStep 2: 127 - 12 = 1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4097, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 94 + 33 = 127 \\nStep 2: 127(...TRUNCATED)
{"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
7