Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
7
989
answer
stringlengths
0
28
task_config
stringclasses
15 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
784
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
16k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
16.1k
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
33.1k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
2
16.8k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-09-24 00:00:00
2025-09-24 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 [43, 72], create an equation that equals 115. You can use basic arithmetic operations (+, -, *, /) and each number can only ...
43 + 72
countdown_2arg
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 [43, 72], create an equation that equals 115. You can use basic arithmetic operations (+, -, *, /) ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 204, \"numbers\": [43, 72], \"target\": 115, \"expression\": \"43 + 72\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 204, "numbers": [43, 72], "target": 115, "expression": "43 + 72"}
null
null
null
null
null
null
[ "<think>\nFirst, I have the numbers [43, 72] and need to make an equation that equals 115 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nI need to combine these two numbers to get 115. Since 115 is larger than both 43 and 72 individually...
[ 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}
[ true, true, true, false ]
[ "43 + 72 = 115", "43 + 72 = 115", "72 + 43 = 115", "tags.\n\nAlso, in the single equation, I should write it clearly.\n\nLooking back at the example: they showed both options.\n\nI think either is fine.\n\nTo be precise, I'll provide both for the sake of completeness.\n\nBut typically, the problem expects one...
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 5222, "span_end": 5235, "original_span": "43 + 72 = 115"}, {"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 5466, "span_end": 5481, "original_span": "43 + 72 = 115"}, {"extractio...
[{"is_correct": true, "error": null, "answer_block": "43 + 72 = 115", "final_answer": 115.0}, {"is_correct": true, "error": null, "answer_block": "43 + 72 = 115", "final_answer": 115.0}, {"is_correct": true, "error": null, "answer_block": "72 + 43 = 115", "final_answer": 115.0}, {"is_correct": false, "error": "Incorrec...
[ [ false, true ], [ true, true, true ], [ false, true ], [ false ] ]
[ [ "tags.\n\nAlso, for the single equation, it's concise.\n\nBut let me confirm if there's a trick or requirement.\n\nThe problem says: \"create an equation that equals 115\" and \"each number can only be used once.\"\n\nHere, I used both numbers once, added them together.\n\nNo issue.\n\nPerhaps they expect a m...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3801, "span_text": "tags.\n\nAlso, for the single equation, it's concise.\n\nBut let me confirm if there's a trick or requirement.\n\nThe problem says: \"create an equation that equals 115\" and \"each number can only be used once.\"\n\nHere, I used both n...
[[{"is_correct": false, "error": "Error evaluating final answer", "answer_block": "tags.\n\nAlso, for the single equation, it's concise.\n\nBut let me confirm if there's a trick or requirement.\n\nThe problem says: \"create an equation that equals 115\" and \"each number can only be used once.\"\n\nHere, I used both nu...
{ "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, ...
2025-09-24
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 [41, 12], create an equation that equals 492. You can use basic arithmetic operations (+, -, *, /) and each number can only ...
12*41
countdown_2arg
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 [41, 12], create an equation that equals 492. You can use basic arithmetic operations (+, -, *, /) ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 229, \"numbers\": [41, 12], \"target\": 492, \"expression\": \"12*41\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 229, "numbers": [41, 12], "target": 492, "expression": "12*41"}
null
null
null
null
null
null
[ "<think>\nFirst, I have the numbers [41, 12] and need to make 492 using addition, subtraction, multiplication, and division. Each number can be used only once.\n\nI should consider what operations might get me close to 492. Since 492 is larger than both 41 and 12, I probably need to multiply or add something.\n\nLe...
[ 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}
[ true, false, true, true ]
[ "Step 1: 41 * 12 = 492", "41 × 12 = 492", "(41 * 12) = 492", "(41 * 12)" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 5125, "span_end": 5148, "original_span": "Step 1: 41 * 12 = 492"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 5884, "span_end": 5899, "original_span": "41 \u00d7 12 = 492"}...
[{"is_correct": true, "error": null, "answer_block": "Step 1: 41 * 12 = 492", "final_answer": 492.0}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "41 \u00d7 12 = 492", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "(41 * 12) = 492", "final_answer": 492.0}...
[ [ true, true ], [ false, false, false, false ], [ true, true, true ], [ false, true, false, true ] ]
[ [ "Step 1: 41 * 12 = 492", "Step 1: 41 * 12 = 492" ], [ "(your answer)", "41 × 12 = 492", "41 × 12 = 492", "41 × 12 = 492" ], [ "tags.\n\nAlso, in the steps, I should show the operations clearly.\n\nSo, for example:\n\nStep 1: Multiply 41 and 12 to get 492.\n\nOr Step 1: 41 * 12 ...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2961, "span_text": "Step 1: 41 * 12 = 492", "extraction_type": "internal", "span_start": 2961, "span_end": 2984, "original_span": "Step 1: 41 * 12 = 492"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 5125, "span_text": "Step 1: 41 * 12 = ...
[[{"is_correct": true, "error": null, "answer_block": "Step 1: 41 * 12 = 492", "final_answer": 492.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 41 * 12 = 492", "final_answer": 492.0}], [{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": n...
{ "flips_by": [ 0, 0, 0, 1 ], "flips_total": 1, "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, ...
2025-09-24
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 [12, 33], create an equation that equals 396. You can use basic arithmetic operations (+, -, *, /) and each number can only ...
12*33
countdown_2arg
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 [12, 33], create an equation that equals 396. You can use basic arithmetic operations (+, -, *, /) ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 243, \"numbers\": [12, 33], \"target\": 396, \"expression\": \"12*33\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 243, "numbers": [12, 33], "target": 396, "expression": "12*33"}
null
null
null
null
null
null
[ "<think>\nFirst, I have the numbers [12, 33] and need to make 396 using addition, subtraction, multiplication, and division. Each number can be used only once.\n\nI should consider what operations might get me close to 396. Since 396 is larger than both 12 and 33, I probably need to multiply or add something.\n\nLe...
[ 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}
[ false, true, false, false ]
[ "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen the next step is implied.\n\nIn the example, they wrote Step 1: 1+2=3, Step 2: 3/3=1, so Step 2 uses the result.\n\nSimilarly, here, Step 1: 33×12=396.\n\nBu...
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 3681, "span_end": 5749, "original_span": "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen the next step is implied...
[{"is_correct": false, "error": "Could not evaluate line: In the example, they wrote Step 1: 1+2=3, Step 2: 3/3=1, so Step 2 uses the result.", "answer_block": "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen t...
[ [ false ], [ false, true ], [ false ], [ false ] ]
[ [ "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen the next step is implied.\n\nIn the example, they wrote Step 1: 1+2=3, Step 2: 3/3=1, so Step 2 uses the result.\n\nSimilarly, here, Step 1: 33×12=396....
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3681, "span_text": "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen the next step is implied.\n\nIn the example, they wrote Step 1: 1+2=3, Step 2:...
[[{"is_correct": false, "error": "Could not evaluate line: In the example, they wrote Step 1: 1+2=3, Step 2: 3/3=1, so Step 2 uses the result.", "answer_block": "tags.\n\nAlso, for steps, it might be like:\n\nStep 1: Multiply 33 by 12 to get 396.\n\nBut in steps, it shows the intermediate result, which is 396.\n\nThen ...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.25, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, ...
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
69 + 53
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 293, \\\"numbers(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 293, \"numbers\": [53, 69], \"target\": 122, (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [53, 69] and need to make 122 using basic arithmetic operations: addit(...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)
[ true, false, true, false ]
["53 + 69 = 122","tags.\n\nAlso, in the thinking, I considered different ways, but this works best.\(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"53 + 69 = 122\", \"final_answer\": 122(...TRUNCATED)
[ [ true, true ], [ false ], [ true ], [ false, false, false ] ]
[["53 + 69 = 122","53 + 69 = 122"],["tags.\n\nAlso, in the thinking, I considered different ways, bu(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2806, \"span_text\": \"53 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"53 + 69 = 122\", \"final_answer\": 12(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
52 + 58
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 325, \\\"numbers(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 325, \"numbers\": [58, 52], \"target\": 110, (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [58, 52] and need to make an equation that equals 110 using basic arit(...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)
[ true, true, true, true ]
[ "Step 1: 58 + 52 = 110", "(58 + 52)", "58 + 52", "Step 1: 58 + 52 = 110" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 58 + 52 = 110\", \"final_answe(...TRUNCATED)
[ [ true ], [ false, true ], [ false, false, true ], [ false, true, true ] ]
[["Step 1: 58 + 52 = 110"],["tags.\n\nAlso, in the single equation, I can write it as 58 + 52 = 110,(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5019, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 58 + 52 = 110\", \"final_answ(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
55 + 91
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 460, \\\"numbers(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 460, \"numbers\": [55, 91], \"target\": 146, (...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [55, 91] and need to make an equation that equals 146 using add(...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)
[ false, false, true, true ]
["tags.\n\nAlso, in the example, for the equation, they wrote \"(1 + 2) / 3\" which implies it equal(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate line: Similarly, I can write 55 + 91 = 146(...TRUNCATED)
[ [ false, true, false ], [ false ], [ false, true ], [ true ] ]
[["(your answer)","55 + 91 = 146","tags.\n\nAlso, in the example, for the equation, they wrote \"(1 (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1782, \"span_text\": \"(you(...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)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
42 + 84
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 541, \\\"numbers(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 541, \"numbers\": [42, 84], \"target\": 126, (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [42, 84] and need to make an equation that equals 126 using basic arit(...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)
[ true, true, true, true ]
[ "42 + 84 = 126", "42 + 84", "Step 1: 84 + 42 = 126", "Step 1: 42 + 84 = 126" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"42 + 84 = 126\", \"final_answer\": 126(...TRUNCATED)
[ [ false, true ], [ false, false, false, false, true, true ], [ false, true ], [ true ] ]
[["tags.\n\nAlso, in the single equation, I should use parentheses or something to ensure order, but(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1749, \"span_text\": \"tags(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: For example, 84 / 42 = 2, then 2 * (...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
41 + 71
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 693, \\\"numbers(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 693, \"numbers\": [71, 41], \"target\": 112, (...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [71, 41] and need to make an equation that equals 112 using basic arit(...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)
[ true, true, false, false ]
["71 + 41 = 112","71 + 41 = 112","Step 1: Multiply 41 by 2 to get 82.\nStep 2: Add 71 to 82 to get 1(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"71 + 41 = 112\", \"final_answer\": 112(...TRUNCATED)
[ [ false, true ], [ false, true ], [ false, false ], [ false ] ]
[["(your answer)","71 + 41 = 112"],["tags.\n\nAlso, in the instruction, it says \"give your answer i(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3077, \"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":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
54 + 60
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1044, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 1044, \"numbers\": [60, 54], \"target\": 114,(...TRUNCATED)
null
null
null
null
null
null
["<think>\nFirst, I have the numbers [60, 54] and need to make 114 using addition, subtraction, mult(...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)
[ true, true, false, false ]
["60 + 54 = 114","60 + 54 = 114","tags.\n\nAlso, in the text, I need to explain the reasoning.\n\nBu(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"60 + 54 = 114\", \"final_answer\": 114(...TRUNCATED)
[ [ true ], [ true, true, true ], [ false, false ], [ false ] ]
[["60 + 54 = 114"],["tags.\n\nSo, for example:\n\n<answer>\n60 + 54 = 114","Step 1: 60 + 54 = 114","(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3623, \"span_text\": \"60 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"60 + 54 = 114\", \"final_answer\": 11(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-09-24
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
90 + 14
countdown_2arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1236, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 1236, \"numbers\": [90, 14], \"target\": 104,(...TRUNCATED)
null
null
null
null
null
null
["<think>\nI have the numbers [90, 14] and need to make an equation that equals 104 using basic arit(...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)
[ true, false, true, true ]
["Step 1: 90 + 14 = 104","tags.\n\nAlso, in the single equation format, it should be the expression (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 90 + 14 = 104\", \"final_answe(...TRUNCATED)
[[true,true,false,true],[true,true,false],[false,false,true],[false,false,false,false,true,true,true(...TRUNCATED)
[["tags.\n\nAlso, in the thinking part, I should present it clearly.\n\nSo, for my response:\n\nI'll(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2109, \"span_text\": \"tags(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"tags.\\n\\nAlso, in the thinking part(...TRUNCATED)
{"flips_by":[1,1,0,0],"flips_total":2,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED)
2025-09-24
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
8