Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
7
989
answer
stringlengths
0
28
task_config
stringclasses
13 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
metadata
stringlengths
41
152
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
2.76k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
2.98k
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
8.16k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-10-27 00:00:00
2025-10-27 00:00:00
answer_index
int64
0
4
answer_key
stringclasses
5 values
choices
stringlengths
4
148
id
stringlengths
7
34
difficulty
stringclasses
1 value
domain
stringclasses
1 value
evaluation_type
stringclasses
1 value
expected_answer_format
stringclasses
1 value
original_answer
stringlengths
48
1.07k
source
stringclasses
601 values
task_type
stringclasses
1 value
variant
stringclasses
1 value
acronym
stringclasses
341 values
formed_acronym
stringclasses
341 values
word_count
int64
4
8
words
listlengths
4
8
length
int64
4
8
letters
stringclasses
600 values
question_idx
int64
0
1.32k
response_idx
int64
0
3
original_response_idx_in_16
int64
0
3
original_response
stringlengths
275
253k
budget_forced_continuations
dict
model_responses__budget_forced
listlengths
2
4
model_responses__budget_forced__eval_is_correct
listlengths
2
4
model_responses__budget_forced__eval_extracted_answers
listlengths
2
4
model_responses__budget_forced__eval_extraction_metadata
stringlengths
120
10.9k
model_responses__budget_forced__eval_evaluation_metadata
stringlengths
112
10.9k
model_responses__budget_forced__internal_answers__eval_is_correct
listlengths
2
4
model_responses__budget_forced__internal_answers__eval_extracted_answers
listlengths
2
4
model_responses__budget_forced__internal_answers__eval_extraction_metadata
stringlengths
192
60.4k
model_responses__budget_forced__internal_answers__eval_evaluation_metadata
stringlengths
70
38.2k
model_responses__budget_forced__metrics
dict
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
97*6 - 92 - 15
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 682, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 682, \"numbers\": [6, 15, 97, 92], \"target\"(...TRUNCATED)
["<think>\nI have the numbers [6, 15, 97, 92] and I need to make an equation that equals 475 using b(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ null, "(92 / (1/5)) + 15", "(97 × 6) − (92 + 15) = 475", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false ], [ false ], [] ]
[ [], [ "(92 / (1/5)) + 15" ], [ "(97 × 6) − (92 + 15) = 475" ], [] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5338, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Expression uses an unavailable or repeated number\", \"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)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
267
3
3
"<think>\nI have the numbers [6, 15, 97, 92] and need to make 475 using basic arithmetic operations:(...TRUNCATED)
{"response":"<think>\nI have the numbers [6, 15, 97, 92] and need to make 475 using basic arithmetic(...TRUNCATED)
["<think>\nI have the numbers [6, 15, 97, 92] and need to make 475 using basic arithmetic operations(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
5*(86 + 73) - 61
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 949, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 949, \"numbers\": [86, 61, 5, 73], \"target\"(...TRUNCATED)
["<think>\nI have the numbers [86, 61, 5, 73] and need to make an equation that equals 734 using bas(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "(86 \\times 5) - 61", "734 / 5 * 5", "(86 × 61) − 734", "73 * 10 + 4" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(86 \\\\(...TRUNCATED)
[ [ false ], [ false, false, false ], [ false ], [ false, false ] ]
[["(86 \\times 5) - 61"],["(1 + 2) / 3","734 / 5 * 5","734 / 5 * 5"],["(86 × 61) − 734"],["73 * 1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7926, \"span_text\": \"(86 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(86 \\\(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
419
0
0
"<think>\nI have the numbers [86, 61, 5, 73] and need to make an equation that equals 734 using basi(...TRUNCATED)
{"response":"<think>\nI have the numbers [86, 61, 5, 73] and need to make an equation that equals 73(...TRUNCATED)
["<think>\nI have the numbers [86, 61, 5, 73] and need to make an equation that equals 734 using bas(...TRUNCATED)
[ false, false, false, false ]
[ "(86 \\times 5) - 61", "(86 × 5) - 61", "(86 × 5) - 61", "(86 × 5) - 61" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(86 \\\\(...TRUNCATED)
[ [ false ], [ false ], [ false ], [ false ] ]
[ [ "(86 \\times 5) - 61" ], [ "(86 × 5) - 61" ], [ "(86 × 5) - 61" ], [ "(86 × 5) - 61" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7926, \"span_text\": \"(86 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(86 \\\(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
88 - 43 + 47 + 30
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1146, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 1146, \"numbers\": [30, 47, 43, 88], \"target(...TRUNCATED)
["<think>\nI have the numbers [30, 47, 43, 88] and need to make an equation that equals 122 using ba(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, true, false, true ]
[null,"(47 + 88) - (43 - 30) = 122","Step 1: 30 + 47 = 77 \nStep 2: 77 + 43 = 120 \nStep 3: 120 - (...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ true ], [ false ], [ true ] ]
[[],["(47 + 88) - (43 - 30) = 122"],["Step 1: 30 + 47 = 77 \nStep 2: 77 + 43 = 120 \nStep 3: 120 -(...TRUNCATED)
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6956, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"(47 + 88) - (43 - 30) = 122\", \"(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
538
2
2
"<think>\nFirst, I have the numbers: 30, 47, 43, and 88. I need to use each exactly once with basic (...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers: 30, 47, 43, and 88. I need to use each exactly once(...TRUNCATED)
["<think>\nFirst, I have the numbers: 30, 47, 43, and 88. I need to use each exactly once with basic(...TRUNCATED)
[ false, false, false, false ]
["Step 1: 30 + 47 = 77 \nStep 2: 77 + 43 = 120 \nStep 3: 120 - 43 = 77 (but redundant, as 77 is us(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 3: 120 - 43 = 77 (but redundant(...TRUNCATED)
[ [ false ], [ false ], [ false ], [ false ] ]
[["Step 1: 30 + 47 = 77 \nStep 2: 77 + 43 = 120 \nStep 3: 120 - 43 = 77 (but redundant, as 77 is u(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8574, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 3: 120 - 43 = 77 (but redundan(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
12*71 - 83 - 14
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 638, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 638, \"numbers\": [71, 14, 12, 83], \"target\(...TRUNCATED)
["<think>\nI have the numbers [71, 14, 12, 83] and I need to make an equation that equals 755 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
["Step 1: 83 * 12 = 996 \nStep 2: 71 * 14 = 994 \nStep 3: 996 - 994 = 2 \nStep 4: Add 753 to the (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 5: Therefore, 996 - 994 + 753 =(...TRUNCATED)
[ [ false, false ], [ false, false ], [], [] ]
[["Step 1: 83 * 12 = 996\nStep 2: 71 * 14 = 994\nStep 3: 996 - 994 = 2, but we need to show the resu(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10126, \"span_text\": \"Ste(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 3: 996 - 994 = 2, but we need (...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
241
0
0
"<think>\nI have the numbers [71, 14, 12, 83] and I need to make an equation that equals 755 using b(...TRUNCATED)
{"response":"<think>\nI have the numbers [71, 14, 12, 83] and I need to make an equation that equals(...TRUNCATED)
["<think>\nI have the numbers [71, 14, 12, 83] and I need to make an equation that equals 755 using (...TRUNCATED)
[ false, false, false, false ]
["Step 1: 83 * 12 = 996 \nStep 2: 71 * 14 = 994 \nStep 3: 996 - 994 = 2 \nStep 4: Add 753 to the (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 5: Therefore, 996 - 994 + 753 =(...TRUNCATED)
[ [ false, false ], [ false, false ], [ false, false ], [ false, false, false ] ]
[["Step 1: 83 * 12 = 996\nStep 2: 71 * 14 = 994\nStep 3: 996 - 994 = 2, but we need to show the resu(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10126, \"span_text\": \"Ste(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 3: 996 - 994 = 2, but we need (...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
2*(97 - 23) + 32
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1680, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 1680, \"numbers\": [2, 97, 23, 32], \"target\(...TRUNCATED)
["<think>\nI have the numbers [2, 97, 23, 32] and I need to make an equation that equals 180 using b(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ true, false, false, false ]
[ "Step 1: 97 - 23 = 74\nStep 2: 74 * 2 = 148\nStep 3: 148 + 32 = 180", null, null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 97 - 23 = 74\\nStep 2: 74 * 2 (...TRUNCATED)
[ [ true ], [], [], [] ]
[ [ "Step 1: 97 - 23 = 74\nStep 2: 74 * 2 = 148\nStep 3: 148 + 32 = 180" ], [], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 9638, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 97 - 23 = 74\\nStep 2: 74 * 2(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
870
1
1
"<think>\nI have the numbers [2, 97, 23, 32] and I need to make an equation that equals 180 using ba(...TRUNCATED)
{"response":"<think>\nI have the numbers [2, 97, 23, 32] and I need to make an equation that equals (...TRUNCATED)
["<think>\nI have the numbers [2, 97, 23, 32] and I need to make an equation that equals 180 using b(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
27*29 - 96 - 39
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 253, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 253, \"numbers\": [96, 27, 29, 39], \"target\(...TRUNCATED)
["<think>\nI have the numbers [96, 27, 29, 39] and I need to make an equation that equals 648 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
{}
{}
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
2
3
3
"<think>\nFirst, I have the numbers: 96, 27, 29, and 39. I need to use each exactly once with basic (...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers: 96, 27, 29, and 39. I need to use each exactly once(...TRUNCATED)
["<think>\nFirst, I have the numbers: 96, 27, 29, and 39. I need to use each exactly once with basic(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
88 - 32 + 89 - 32
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1014, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 1014, \"numbers\": [89, 88, 32, 32], \"target(...TRUNCATED)
["<think>\nI have the numbers [89, 88, 32, 32] and I need to make an equation that equals 113 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, true, false ]
[null,"Step 1: Multiply 88 and 32 to get 2848.\nStep 2: Divide 2848 by 32 to get 89.","(89 - 32) + 8(...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false, false ], [ false, true ], [ false, false, false ] ]
[[],["Step 1: Multiply 88 and 32 to get 2848.\nStep 2: Divide 2848 by 32 to get 89.","Step 1: Multip(...TRUNCATED)
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8226, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Error evaluating final answer\", \"answer_block\": \"Ste(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
467
2
2
"<think>\nI have the numbers [89, 88, 32, 32] and need to make an equation that equals 113 using bas(...TRUNCATED)
{"response":"<think>\nI have the numbers [89, 88, 32, 32] and need to make an equation that equals 1(...TRUNCATED)
["<think>\nI have the numbers [89, 88, 32, 32] and need to make an equation that equals 113 using ba(...TRUNCATED)
[ true, true, true, true ]
[ "(89 - 32) + 88 - 32", "(89 - 32) + 88 - 32", "(89 - 32) + 88 - 32", "(89 - 32) + 88 - 32" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(89 - 32) + 88 - 32\", \"final_answer\(...TRUNCATED)
[ [ false, true ], [ false, true ], [ false, true ], [ false, true ] ]
[["(1 + 2) / 3","(89 - 32) + 88 - 32"],["(1 + 2) / 3","(89 - 32) + 88 - 32"],["(1 + 2) / 3","(89 - 3(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5333, \"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,"skill_cou(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
62 + 76 + 79 - 83
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1467, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 1467, \"numbers\": [76, 83, 62, 79], \"target(...TRUNCATED)
["<think>\nI have the numbers [76, 83, 62, 79] and I need to make an equation that equals 134 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, true, true ]
["Step 1: 76 + 79 = 155 \nStep 2: 155 - 83 = 72 \nStep 3: 72 - 62 = 134","(83 - 79) * (76 / 62)","(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Incorrect arithmetic in line: Step 3: 72 - 62 = 134\", \"answ(...TRUNCATED)
[ [ false, true, false ], [ false, false, false, false ], [ true ], [ true ] ]
[["(your answer)","Step 1: 76 + 79 = 155\n\nStep 2: 83 - 62 = 21\n\nStep 3: 155 - 21 = 134","Step 1:(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11804, \"span_text\": \"(yo(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[1,0,0,0],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
732
2
2
"<think>\nFirst, I have the numbers: 76, 83, 62, and 79. I need to use each exactly once with basic (...TRUNCATED)
{"response":"<think>\nFirst, I have the numbers: 76, 83, 62, and 79. I need to use each exactly once(...TRUNCATED)
["<think>\nFirst, I have the numbers: 76, 83, 62, and 79. I need to use each exactly once with basic(...TRUNCATED)
[ true, false, false, false ]
["Step 1: 76 + 79 = 155 \nStep 2: 155 - 83 = 72 \nStep 3: 72 + 62 = 134","Step 1: 76 - 83 = 21 \n(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 76 + 79 = 155 \\nStep 2: 155 (...TRUNCATED)
[ [ true ], [ false ], [ false ], [ false ] ]
[["Step 1: 76 + 79 = 155 \nStep 2: 155 - 83 = 72 \nStep 3: 72 + 62 = 134"],["Step 1: 76 - 83 = 21 (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7794, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 76 + 79 = 155 \\nStep 2: 155(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
22*43/2 + 6
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1859, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 1859, \"numbers\": [6, 2, 22, 43], \"target\"(...TRUNCATED)
["<think>\nFirst, I have the numbers: 6, 2, 22, and 43. I need to use each exactly once with basic a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, true, false, false ]
["Step 1: 22 - 6 = 16 \nStep 2: 43 * 11 = 473 \nStep 3: 473 + 16 = 489","(22 / 2) * 43 + 6","(43 (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 2: 43 * 11 = 473 \", \"a(...TRUNCATED)
[ [ false, false ], [ false, false, false, true, true ], [ false, false ], [] ]
[["Step 1: 22 - 6 = 16\nStep 2: 43 * 11 = 473\nStep 3: 473 + 16 = 489","Step 1: 22 - 6 = 16 \nStep (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7448, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 2: 43 * 11 = 473\", \"an(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
971
3
3
"<think>\nI have the numbers [6, 2, 22, 43] and need to make an equation that equals 479 using basic(...TRUNCATED)
{"response":"<think>\nI have the numbers [6, 2, 22, 43] and need to make an equation that equals 479(...TRUNCATED)
["<think>\nI have the numbers [6, 2, 22, 43] and need to make an equation that equals 479 using basi(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
2*65 + 2 + 4
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 797, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 797, \"numbers\": [2, 4, 2, 65], \"target\": (...TRUNCATED)
["<think>\nFirst, I have the numbers [2, 4, 2, 65]. I need to use each one exactly once with basic a(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
"{\"api_url\": \"http://10.32.37.28:9080/v1\", \"backend\": \"litellm\", \"chat_template_applied\": (...TRUNCATED)
"{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED)
[ false, false, false, false ]
[ "65 * 2 + 4", "65 * 2 + 6", null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED)
[ [ false ], [ false, false, false, false ], [], [] ]
[ [ "65 * 2 + 4" ], [ "(your answer)", "65 * 2 + 6", "65 * 2 + 6", "65 * 2 + 6" ], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7447, \"span_text\": \"65 *(...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)
2025-10-27
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
null
339
2
2
"<think>\nI have the numbers [2, 4, 2, 65] and need to make an equation that equals 136 using basic (...TRUNCATED)
{"response":"<think>\nI have the numbers [2, 4, 2, 65] and need to make an equation that equals 136 (...TRUNCATED)
["<think>\nI have the numbers [2, 4, 2, 65] and need to make an equation that equals 136 using basic(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
3