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
786
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
1.61k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
1.78k
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
5.56k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
2
3.04k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-11-21 00:00:00
2025-11-21 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 need to make 125 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 125. Since 96 and 97 are both large and close to each other, may...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://10.32.36.210:10080/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_Qwen2.5-7B_R1Distill-sft...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sft", "n_responses": 4}
[ true, true, true, true ]
[ "(96 + 97) - 68 = 125", "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125" ]
[{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 5019, "span_end": 5041, "original_span": "(96 + 97) - 68 = 125"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 4985, "span_end": 5029, "original_span": "Step 1: 97 - 68 = 29\...
[{"is_correct": true, "error": null, "answer_block": "(96 + 97) - 68 = 125", "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": "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 1...
[ [ true, true, true ], [ true, true ], [ true, true, true ], [ true ] ]
[ [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "Step 1: 96 + 97 = 193 \nStep 2: 193 - 68 = 125", "(96 + 97) - 68 = 125" ], [ "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125" ], [ "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "St...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3446, "span_text": "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "extraction_type": "internal", "span_start": 3446, "span_end": 3492, "original_span": "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125"}, {"pattern_used": "answer tag", "confidence": 1.0, "p...
[[{"is_correct": true, "error": null, "answer_block": "Step 1: 96 + 97 = 193\nStep 2: 193 - 68 = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 96 + 97 = 193 \nStep 2: 193 - 68 = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "(96 + 97) - 6...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 4, "pass_at_n": 1, "percent_correct": 1, "total_responses": 4 }
2025-11-21
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>\nFirst, I have the numbers [21, 80, 46] and I need to use them to make 105 using addition, subtraction, multiplication, and division. Each number can only be used once.\n\nI should consider possible combinations. Since 105 is larger than all the numbers except 80, but 80 is less than 105, so I probably nee...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://10.32.36.210:10080/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_Qwen2.5-7B_R1Distill-sft...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sft", "n_responses": 4}
[ true, true, true, true ]
[ "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "80 + 46 - 21", "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105", "Step 1: 46 - 21 = 25\nStep 2: 80 + 25 = 105" ]
[{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 6199, "span_end": 6245, "original_span": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 7461, "span_end": 7475, "original_span...
[{"is_correct": true, "error": null, "answer_block": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "final_answer": 105.0}, {"is_correct": true, "error": null, "answer_block": "80 + 46 - 21", "final_answer": 105.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105", "fi...
[ [ true, false, true ], [ true, true ], [ true ], [ true, false, true ] ]
[ [ "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", "80 + 46 - 21" ], [ "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105" ], [ "Step 1: 46 - 21 = 25\nStep 2: 80 + 25 = 105", "(your answ...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4557, "span_text": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "extraction_type": "internal", "span_start": 4557, "span_end": 4603, "original_span": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105"}, {"pattern_used": "answer tag", "confidence": 1.0, "p...
[[{"is_correct": true, "error": null, "answer_block": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "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": "Step 1: 80 + 46 = 12...
{ "flips_by": [ 1, 0, 0, 1 ], "flips_total": 2, "num_correct": 4, "pass_at_n": 1, "percent_correct": 1, "total_responses": 4 }
2025-11-21
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 [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, /) and each number can on...
6*96 - 76
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 [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5002, \"numbers\": [6, 76, 96], \"target\": 500, \"expression\": \"6*96 - 76\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5002, "numbers": [6, 76, 96], "target": 500, "expression": "6*96 - 76"}
null
null
null
null
null
null
[ "<think>\nI have the numbers [6, 76, 96] and need to make 500 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 500. Since 500 is a fairly large number, multiplication might be ...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://10.32.36.210:10080/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_Qwen2.5-7B_R1Distill-sft...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sft", "n_responses": 4}
[ false, false, true, true ]
[ "(96 × 6) − 76", "(96 × 6) − 76 = 500", "(96 * 6) - 76 = 500", "(96 * 6) - 76" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 4856, "span_end": 4871, "original_span": "(96 \u00d7 6) \u2212 76"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 5853, "span_end": 5874, "original_span": "(96 \u00d7 6) \u22...
[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(96 \u00d7 6) \u2212 76", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(96 \u00d7 6) \u2212 76 = 500", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "...
[ [ false, false ], [ false ], [ true, true, true, true ], [ false, true ] ]
[ [ "(your answer)", "(96 × 6) − 76" ], [ "(96 × 6) − 76 = 500" ], [ "(96 * 6) - 76", "Step 1: 96 * 6 = 576\nStep 2: 576 - 76 = 500", "Step 1: 96 * 6 = 576 \nStep 2: 576 - 76 = 500", "(96 * 6) - 76 = 500" ], [ "(96 × 6) − 76", "(96 * 6) - 76" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2494, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2494, "span_end": 2507, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 4856, "span_text": "(96 \u00d7 6) \u2212 76", "extract...
[[{"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": "(96 \u00d7 6) \u2212 76", "final_answer": null}], [{"is_correct": false, "error": "Could not evaluate expression", "a...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 2, "pass_at_n": 1, "percent_correct": 0.5, "total_responses": 4 }
2025-11-21
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 [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, /) and each number can on...
42*(12 + 3)
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 [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 630, \"expression\": \"42*(12 + 3)\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5003, "numbers": [42, 12, 3], "target": 630, "expression": "42*(12 + 3)"}
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, subtraction, multiplication, and division. Each number can only be used once.\n\nI should consider what operations might get me close to 630. Since 630 is a fairly large number, multiplication might be involved becaus...
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url": "http://10.32.36.210:10080/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_Qwen2.5-7B_R1Distill-sft...
{"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sft", "n_responses": 4}
[ false, false, true, false ]
[ "(12 + 3) × 42", "42 × (12 + 3) = 630", "42 * (12 + 3)", "(12 + 3) × 42" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 4485, "span_end": 4500, "original_span": "(12 + 3) \u00d7 42"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 4582, "span_end": 4603, "original_span": "42 \u00d7 (12 + 3) = 63...
[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(12 + 3) \u00d7 42", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "42 \u00d7 (12 + 3) = 630", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "42 * (12 +...
[ [ false, false ], [ false, false ], [ false, false, false, true, true ], [ false, false, false ] ]
[ [ "(your answer)", "(12 + 3) × 42" ], [ "(your answer)", "42 × (12 + 3) = 630" ], [ "(your answer)", "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1", "(1 + 2) / 3", "42 * (12 + 3)", "42 * (12 + 3)" ], [ "(your answer)", "(12 + 3) × 42", "(12 + 3) × 42" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2738, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2738, "span_end": 2751, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 4485, "span_text": "(12 + 3) \u00d7 42", "extraction_t...
[[{"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": "(12 + 3) \u00d7 42", "final_answer": null}], [{"is_correct": false, "error": "Could not evaluate expression", "answer...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.25, "total_responses": 4 }
2025-11-21
"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://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ true, true, true, true ]
["86 + (69 - 52) = 103","69 + 86 - 52","Step 1: 86 + 69 = 155 \nStep 2: 155 - 52 = 103","(86 - 52) (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"86 + (69 - 52) = 103\", \"final_answer(...TRUNCATED)
[ [ false, false, true, true, true ], [ true ], [ true ], [ false, true ] ]
[["(your answer)","(your answer)","Step 1: 69 - 52 = 17\nStep 2: 86 + 17 = 103","86 + (69 - 52) = 10(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3405, \"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,"total_res(...TRUNCATED)
2025-11-21
"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://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ true, true, true, true ]
["Step 1: 63 * 7 = 441 \nStep 2: 441 - 87 = 354","Step 1: 63 * 7 = 441\nStep 2: 441 - 87 = 354","St(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 63 * 7 = 441 \\nStep 2: 441 -(...TRUNCATED)
[ [ false, true ], [ true, true ], [ false, false, false, false, true ], [ false, false, true, true ] ]
[["(your answer)","Step 1: 63 * 7 = 441 \nStep 2: 441 - 87 = 354"],["Step 1: 63 * 7 = 441\nStep 2: (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2708, \"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,"total_res(...TRUNCATED)
2025-11-21
"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, 19] and I need to make an equation that equals 102 usin(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ false, false, false, true ]
["(8 × 19) − 50","(8 × 19) − 50 = 102","Step 1: 19 × 8 = 152 \nStep 2: 152 − 50 = 102","St(...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\": \"(8 \\u00(...TRUNCATED)
[ [ false, false ], [ false ], [ false, false, false ], [ false, true, false, true ] ]
[["(your answer)","(8 × 19) − 50"],["(8 × 19) − 50 = 102"],["(your answer)","Step 1: 19 × 8 =(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5011, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,1],"flips_total":1,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"total_re(...TRUNCATED)
2025-11-21
"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>\nI have the numbers [38, 46, 40] and need to make an equation that equals 124 using basic (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ true, true, true, true ]
["46 + 40 + 38 = 124","Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124","46 + 40 + 38","Step 1: 38 + 46 (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"46 + 40 + 38 = 124\", \"final_answer\"(...TRUNCATED)
[ [ false, true, true, true ], [ true, true, true ], [ true, false, false, true, true ], [ true, true ] ]
[["(1 + 2) / 3","46 + 40 + 38","Step 1: 46 + 40 = 86 \nStep 2: 86 + 38 = 124","46 + 40 + 38 = 124"](...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3849, \"span_text\": \"(1 +(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED)
{"flips_by":[0,0,1,0],"flips_total":1,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"total_res(...TRUNCATED)
2025-11-21
"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 need to make 132 using basic arithmetic operations: a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ true, true, true, true ]
[ "92 + 21 + 19 = 132", "92 + 21 + 19 = 132", "92 + 21 + 19", "92 + 21 + 19 = 132" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"92 + 21 + 19 = 132\", \"final_answer\"(...TRUNCATED)
[ [ false, true ], [ false, true ], [ false, true ], [ true ] ]
[["(1 + 2) / 3","92 + 21 + 19 = 132"],["(your answer)","92 + 21 + 19 = 132"],["(1 + 2) / 3","92 + 21(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3102, \"span_text\": \"(1 +(...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":4,"pass_at_n":1,"percent_correct":1.0,"total_res(...TRUNCATED)
2025-11-21
"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>\nI have the numbers [23, 21, 7] and need to make 322 using basic arithmetic operations: ad(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.36.210:10080/v1\", \"backend\": \"litellm\", \"chat_template_applied\"(...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-sft_Qwen2.5-7B_R1Distill-sft-sf(...TRUNCATED)
[ true, true, false, false ]
["(21 - 7) * 23","(23 * (21 - 7))","Step 1: 21 - 7 = 14\nStep 2: 14 × 23 = 322","23 × (21 − 7) =(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(21 - 7) * 23\", \"final_answer\": 322(...TRUNCATED)
[ [ true, true ], [ false, true ], [ false ], [ false, false ] ]
[["(21 - 7) * 23","(21 - 7) * 23"],["(your answer)","(23 * (21 - 7))"],["Step 1: 21 - 7 = 14\nStep 2(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3550, \"span_text\": \"(21 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(21 - 7) * 23\", \"final_answer\": 32(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"total_res(...TRUNCATED)
2025-11-21
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
3