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
dict
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
785
1.57k
model_responses__best_of_n_atags__metadata
stringclasses
1 value
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
3.85k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
1.46k
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
2
12.9k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
2
3.51k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-11-17 00:00:00
2025-11-17 00:00:00
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 [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can o...
97 + 96 - 68
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 [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5000, \"numbers\": [96, 97, 68], \"target\": 125, \"expression\": \"97 + 96 - 68\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5000, "numbers": [96, 97, 68], "target": 125, "expression": "97 + 96 - 68"}
null
null
null
null
null
null
[ "<think>\nI have the numbers [96, 97, 68] and I need to make an equation that equals 125 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 125. Since 125 is a bit larger than th...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://127.0.0.1:37245/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": {"chat_template_applied": true, "max_tokens": 16384, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8}, "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-sft", "n_responses": 4}
[ false, true, true, true ]
[ "(96 + 97) + 29", "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "(97 - 68) + 96", "(96 + 97) - 68" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 6855, "span_end": 6869, "original_span": "(96 + 97) + 29"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 5123, "span_end": 5167, "original_span": "Step 1: 97 - 68 = 29\nStep ...
[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(96 + 97) + 29", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "(97 - 68) +...
[ [ false, false ], [ true, true ], [ true ], [ false, true ] ]
[ [ "(your answer)", "(96 + 97) + 29" ], [ "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125" ], [ "(97 - 68) + 96" ], [ "(1 + 2) / 3", "(96 + 97) - 68" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4540, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 4540, "span_end": 4553, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 6855, "span_text": "(96 + 97) + 29", "extraction_type"...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(96 + 97) + 29", "final_answer": 125.0}], [{"is_correct": true, "error": null, "answer_block": "Step 1: 97 ...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 3, "pass_at_n": 1, "percent_correct": 0.75, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, ...
2025-11-17
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 [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can o...
46 + 80 - 21
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 [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5001, \"numbers\": [21, 80, 46], \"target\": 105, \"expression\": \"46 + 80 - 21\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5001, "numbers": [21, 80, 46], "target": 105, "expression": "46 + 80 - 21"}
null
null
null
null
null
null
[ "<think>\nI have the numbers [21, 80, 46] and need to make 105 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 105. Since 105 is larger than all the numbers except 80, multipl...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://127.0.0.1:37245/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": {"chat_template_applied": true, "max_tokens": 16384, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8}, "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-sft", "n_responses": 4}
[ true, false, false, true ]
[ "(80 - 21) + 46", "\\(80 + 46 \\times 21\\)", null, "(80 + 46) - 21 = 105" ]
[{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 7225, "span_end": 7241, "original_span": "(80 - 21) + 46"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 10875, "span_end": 10898, "original_span": "\\(80 + 46 \\times 21\\)"...
[{"is_correct": true, "error": null, "answer_block": "(80 - 21) + 46", "final_answer": 105.0}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "\\(80 + 46 \\times 21\\)", "final_answer": null}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_resul...
[ [ true, false, true ], [ false ], [], [ true, false, true, true ] ]
[ [ "80 - 21 + 46", "(your answer)", "(80 - 21) + 46" ], [ "\\(80 + 46 \\times 21\\)" ], [], [ "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "(your answer)", "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "(80 + 46) - 21 = 105" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4066, "span_text": "80 - 21 + 46", "extraction_type": "internal", "span_start": 4066, "span_end": 4078, "original_span": "80 - 21 + 46"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 5163, "span_text": "(your answer)", "extraction_type": "...
[[{"is_correct": true, "error": null, "answer_block": "80 - 21 + 46", "final_answer": 105.0}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "(80 - 21) + 46", "final_answer": 105.0}], [{"is_corre...
{ "flips_by": [ 1, 0, 0, 1 ], "flips_total": 2, "num_correct": 2, "pass_at_n": 1, "percent_correct": 0.5, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, 0...
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
6*96 - 76
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\\\": 5002, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5002, \"numbers\": [6, 76, 96], \"target\": 5(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers: 6, 76, and 96. I need to use each exactly once with basic arit(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ false, false, false, false ]
[ null, "(6 × 96) ÷ 6", null, "96 × 6 + 24 = 500" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false ], [], [ false ] ]
[ [], [ "(6 × 96) ÷ 6" ], [], [ "96 × 6 + 24 = 500" ] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4542, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(6 (...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
42*(12 + 3)
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\\\": 5003, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 6(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [42, 12, 3] and I need to use them to make 630 using addition, (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ false, false, false, false ]
[ null, "42 × 15 / 3", "42 * 12 / 3 = 630", "(42 × 3) + 504" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false ], [ false, false ], [ false, false, false ] ]
[[],["42 × 15 / 3"],["42 × 12 ÷ 3 = 630","42 * 12 / 3 = 630"],["(42 × 3) + 504","(1 + 2) / 3","((...TRUNCATED)
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7981, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"42 (...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
86 + 69 - 52
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\\\": 5005, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5005, \"numbers\": [86, 69, 52], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [86, 69, 52] and need to make an equation that equals 103 using basic (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ true, true, true, true ]
["(86 + (69 - 52))","Step 1: 86 + 69 = 155\nStep 2: 155 - 52 = 103","(86 + 69) - 52 = 103","Step 1: (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(86 + (69 - 52))\", \"final_answer\": (...TRUNCATED)
[ [ false, true ], [ true, true ], [ true, true, true ], [ true ] ]
[["(your answer)","(86 + (69 - 52))"],["Step 1: 86 + 69 = 155\n\nStep 2: 155 - 52 = 103","Step 1: 86(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3113, \"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)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
63*7 - 87
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\\\": 5006, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5006, \"numbers\": [63, 7, 87], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [63, 7, 87] and need to make 354 using basic arithmetic operations: ad(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ false, false, false, false ]
["\\(63 \\times 7 + 87 = 354\\)","63 * 7 * 87 / 63","Step 1: 87 + 7 = 94 \nStep 2: 94 * 3.843 (not (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"\\\\(63 (...TRUNCATED)
[ [ false, false ], [ false, false ], [ false ], [ false, false ] ]
[["(your answer)","\\(63 \\times 7 + 87 = 354\\)"],["(your answer)","63 * 7 * 87 / 63"],["Step 1: 87(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6930, \"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":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19*8 - 50
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\\\": 5007, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5007, \"numbers\": [8, 50, 19], \"target\": 1(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers: 8, 50, and 19. I need to use each exactly once with basic arit(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ false, false, false, false ]
["Step 1: 50 * 19 = 950 \nStep 2: 950 - 8 = 942","\\(8 + 50 \\times 19\\)","Step 1: 8 * 19 = 152 \(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Incorrect final answer\", \"answer_block\": \"Step 1: 50 * 19(...TRUNCATED)
[ [ false, false ], [ false, false, false, false, false ], [ false, false ], [ false, false, false, false, false ] ]
[["(50 * 19) - 8","Step 1: 50 * 19 = 950 \nStep 2: 950 - 8 = 942"],["(your answer)","(1 + 2) / 3","(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11874, \"span_text\": \"(50(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
40 + 46 + 38
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\\\": 5008, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5008, \"numbers\": [38, 46, 40], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [38, 46, 40] and I need to use them to make 124 using addition,(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ true, true, false, false ]
["(38 + 46) + 40 = 124","Step 1: 46 + 40 = 86 \nStep 2: 86 + 38 = 124","(46 × 40) − 38 = 1788","(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(38 + 46) + 40 = 124\", \"final_answer(...TRUNCATED)
[ [ true ], [ true, false, true ], [ false ], [ false, false, false ] ]
[["(38 + 46) + 40 = 124"],["Step 1: 46 + 40 = 86\nStep 2: 86 + 38 = 124","(1 + 2) / 3","Step 1: 46 +(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4093, \"span_text\": \"(38 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(38 + 46) + 40 = 124\", \"final_answe(...TRUNCATED)
{"flips_by":[0,1,0,0],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19 + 92 + 21
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\\\": 5009, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5009, \"numbers\": [92, 21, 19], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [92, 21, 19] and I need to use them to make 132 using addition, subtra(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ true, true, false, true ]
["Step 1: 92 + 19 = 111 \nStep 2: 111 + 21 = 132","Step 1: 92 + 21 = 113 \nStep 2: 113 + 19 = 132"(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 92 + 19 = 111 \\nStep 2: 111 (...TRUNCATED)
[ [ true, false, true, true ], [ true ], [ false, false, false ], [ false, true ] ]
[["Step 1: 92 + 19 = 111\nStep 2: 111 + 21 = 132","(your answer)","Step 1: 92 + 19 = 111\nStep 2: 11(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2758, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 92 + 19 = 111\\nStep 2: 111 +(...TRUNCATED)
{"flips_by":[1,0,0,0],"flips_total":1,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
2025-11-17
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
23*(21 - 7)
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\\\": 5010, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5010, \"numbers\": [23, 21, 7], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [23, 21, 7] and I need to make an equation that equals 322 usin(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://127.0.0.1:37245/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-0.5B_R1Distill-sft-(...TRUNCATED)
[ false, false, false, false ]
[ "Step 1: 23 * 7 = 147 \nStep 2: 147 / 21 = 7", "(23 * 7) - 21", "(23 × 21) × 7", "(23 × 14)" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Incorrect arithmetic in line: Step 1: 23 * 7 = 147 \", \"ans(...TRUNCATED)
[ [ false, false ], [ false ], [ false, false, false ], [ false ] ]
[["(your answer)","Step 1: 23 * 7 = 147 \nStep 2: 147 / 21 = 7"],["(23 * 7) - 21"],["(your answer)"(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7316, \"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":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
4