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 | eval_date stringdate 2025-09-24 00:00:00 2025-09-24 00:00:00 | model_responses__best_of_n_atags__eval_is_correct listlengths 4 4 | model_responses__best_of_n_atags__eval_extracted_answers listlengths 4 4 | model_responses__best_of_n_atags__eval_extraction_metadata stringlengths 120 4.04k | model_responses__best_of_n_atags__eval_evaluation_metadata stringlengths 224 3.89k | model_responses__best_of_n_atags__internal_answers__eval_is_correct listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extracted_answers listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata stringlengths 192 15.2k ⌀ | model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata stringlengths 70 8.25k ⌀ | model_responses__best_of_n_atags__metrics dict | question_idx int64 0 12.5k | response_idx int64 0 3 | original_response_idx_in_16 int64 0 3 | bf_prompt listlengths 2 2 | original_response stringlengths 279 18.6k | model_responses__bf_continuation listlengths 1 1 | model_responses__bf_continuation__finish_reason_length_flags listlengths 1 1 | model_responses__bf_continuation__length_partial_responses listlengths 1 1 | bf_prompt__bf_continuation__metadata dict | model_responses__bf_continuation__metadata dict | model_responses__budget_forced listlengths 2 2 | model_responses__budget_forced__eval_is_correct listlengths 2 2 | model_responses__budget_forced__eval_extracted_answers listlengths 2 2 | model_responses__budget_forced__eval_extraction_metadata stringlengths 60 23.8k | model_responses__budget_forced__eval_evaluation_metadata stringlengths 112 24k | model_responses__budget_forced__internal_answers__eval_is_correct listlengths 2 2 ⌀ | model_responses__budget_forced__internal_answers__eval_extracted_answers listlengths 2 2 ⌀ | model_responses__budget_forced__internal_answers__eval_extraction_metadata stringlengths 181 47.4k ⌀ | model_responses__budget_forced__internal_answers__eval_evaluation_metadata stringlengths 62 30.5k ⌀ | model_responses__budget_forced__metrics dict |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
22056 x 60696 | 1338710976 | longmult_5dig | longmult | [
{
"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\nWhat is the solution to the multiplication equation below?\n22056 x 60696\n\nGive your answer in the following format:\n<answer>\... | [] | [] | {"metadata": "{\"arg1\": 22056, \"arg2\": 60696, \"solution\": 1338710976}", "task_source": "longmult"} | test | null | null | null | null | null | null | null | null | null | null | null | null | {"arg1": 22056, "arg2": 60696, "solution": 1338710976} | null | null | null | null | null | null | [
"<think>\nFirst, I need to multiply 22056 by 60696. Let me write them down:\n\n22056\n\nand\n\n60696\n\nI should start multiplying from the rightmost digits because that might make it easier due to the large numbers.\n\nIn 60696, the last digit is 6, and in 22056, the last digit is also 6. So when we multiply these... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url": "http://127.0.0.1:41869/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": {"chat_template_applied": true, "max_tokens": 4096, "n": 4, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8}, "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_on... | {"backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only", "n_responses": 4} | 2025-09-24 | [
false,
false,
false,
false
] | [
"13349528336",
"1335312000",
null,
"1338711976"
] | [{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 4587, "span_end": 4598, "original_span": "13349528336"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 4644, "span_end": 4654, "original_span": "1335312000"}, {"extraction_typ... | [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "legacy", "legacy_result": false}] | [
[
false,
false,
false
],
[
false,
false,
false,
false
],
[],
[
false,
false,
false,
false,
false
]
] | [
[
"(your answer)",
"13349528336",
"13349528336"
],
[
"(your answer)",
"(your answer)",
"(your answer)",
"1335312000"
],
[],
[
"(your answer)",
"(your answer)",
"(your answer)",
"1338711976",
"1338711976"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3303, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 3303, "span_end": 3316, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3451, "span_text": "13349528336", "extraction_type": "... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}], [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy",... | {
"flips_by": [
0,
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 11,451 | 1 | 1 | [
{
"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\nWhat is the solution to the multiplication equation below?\n22056 x 60696\n\nGive your answer in the following format:\n<answer>\... | <think>
First, I need to multiply these two numbers: 22056 and 60696. Let me start with some basic calculations or look at patterns.
One thing to notice is that both numbers have digits that might be factors of each other. For example, 22056 has 4 as a factor because 2+2=4, 0+5=5, etc., but I should confirm if it's di... | [
" is there a simpler method? But multiplication is efficient.\n\nPerhaps I can use division to verify, but it's unnecessary.\n\nI think I should go with the direct calculation.\n\nSo, the answer is 1335312000.\n\nIn the boxed output, I'll put it.\n\nBut let me see if I can express it differently.\n\nAnother idea: t... | [
false
] | [
""
] | {
"api_url": "http://127.0.0.1:50597",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 8192,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAU... | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only",
"n_responses": 1
} | [
"<think>\nFirst, I need to multiply these two numbers: 22056 and 60696. Let me start with some basic calculations or look at patterns.\n\nOne thing to notice is that both numbers have digits that might be factors of each other. For example, 22056 has 4 as a factor because 2+2=4, 0+5=5, etc., but I should confirm if... | [
false,
false
] | [
"1335312000",
"1335312000"
] | [{"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 4644, "span_end": 4654, "original_span": "1335312000"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 4644, "span_end": 4654, "original_span": "1335312000"}] | [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}] | [
[
false,
false,
false,
false
],
[
false,
false,
false,
false
]
] | [
[
"(your answer)",
"(your answer)",
"(your answer)",
"1335312000"
],
[
"(your answer)",
"(your answer)",
"(your answer)",
"1335312000"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1040, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 1040, "span_end": 1055, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3514, "span_text": "(your answer)", "extraction_type":... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}], [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy",... | {
"flips_by": [
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0
],
"best_of_n": [
0,
0
],
"reflect_close": [
0,
0
],
"reflect_open": [
0,
0
]... |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 89 + 90 - 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\\\": 5715, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5715, \"numbers\": [90, 89, 76], \"target\": (...TRUNCATED) | null | null | null | null | null | null | ["<think>\nI have the numbers [90, 89, 76] and need to make 103 using basic arithmetic operations: a(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
true,
true,
true,
true
] | [
"Step 1: 89 - 76 = 13 \nStep 2: 90 + 13 = 103",
"90 + (89 - 76)",
"(90 + 89) - 76",
"(90 + 89) - 76"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 89 - 76 = 13 \\nStep 2: 90 + (...TRUNCATED) | [
[
false,
true
],
[
true,
true
],
[
true
],
[
true,
true
]
] | [["(your answer)","Step 1: 89 - 76 = 13 \nStep 2: 90 + 13 = 103"],["90 + (89 - 76)","90 + (89 - 76)(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3629, \"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) | 1,650 | 1 | 1 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nI have the numbers [90, 89, 76] and need to make an equation that equals 103 using basic a(...TRUNCATED) | [" considering the list order, I could use 89 first, but the problem does not specify the order, so (...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nI have the numbers [90, 89, 76] and need to make an equation that equals 103 using basic (...TRUNCATED) | [
true,
true
] | [
"90 + (89 - 76)",
"90 + (89 - 76)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"is_correct\": true, \"error\": null, \"answer_block\": \"90 + (89 - 76)\", \"final_answer\": 10(...TRUNCATED) | [
[
false,
true
],
[
false,
true
]
] | [["tags.\n\nAlso, in the expression, I should show the steps or the equation.\n\nI think I'll provid(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3746, \"span_text\": \"tags(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Could not evaluate line: But to be thorough, I can write it (...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED) |
724 x 155 | 112220 | longmult_3dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 724, \\\"arg2\\\": 155, \\\"solution\\\": 112220}\", \"task_source\(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | {"arg1": 724, "arg2": 155, "solution": 112220} | null | null | null | null | null | null | ["<think>\nFirst, I need to multiply 724 by 155. Let me break it down or use a calculator, but let m(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
false,
true,
true
] | [
"(your answer)",
"108600",
"112220",
"112220"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [
[
false
],
[
false,
false,
false
],
[
false,
true,
false,
false,
true
],
[
false,
true
]
] | [["(your answer)"],["(your answer)","(your answer)","108600"],["(your answer)","112220","(your answe(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2063, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}], [{\"evaluation_method\": \"legacy(...TRUNCATED) | {"flips_by":[0,0,1,0],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED) | 9,112 | 3 | 3 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to multiply 724 by 155. Let me break it down or use a calculator for accurac(...TRUNCATED) | [" \n- Check division: For example, 11,2220 ÷ 1000 = 112.22, but this isn't relevant since the pro(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to multiply 724 by 155. Let me break it down or use a calculator for accura(...TRUNCATED) | [
true,
true
] | [
"112220",
"112220"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [
[
false,
true
],
[
false,
true
]
] | [
[
"(your answer )",
"112220"
],
[
"(your answer )",
"112220"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4212, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED) |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 46*34/4 - 76 + 4 | countdown_5arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1601, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 1601, \"numbers\": [76, 4, 46, 4, 34], \"targ(...TRUNCATED) | null | null | null | null | null | null | ["<think>\nI have the numbers [76, 4, 46, 4, 34] and I need to make an equation that equals 319 usin(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
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) | 3,774 | 1 | 1 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nI have the numbers [76, 4, 46, 4, 34] and need to make an equation that equals 319 using b(...TRUNCATED) | [" The target is 319, which is fairly large. I have numbers like 76 and 46 that are close to each ot(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nI have the numbers [76, 4, 46, 4, 34] and need to make an equation that equals 319 using (...TRUNCATED) | [
false,
false
] | [
null,
null
] | [{"extraction_type": "final"}, {"extraction_type": "final"}] | "[{\"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) | 48*(66 - 47) - 96 + 53 | countdown_5arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 1647, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 1647, \"numbers\": [48, 66, 47, 96, 53], \"ta(...TRUNCATED) | null | null | null | null | null | null | ["<think>\nFirst, I have the numbers: 48, 66, 47, 96, and 53. I need to use each exactly once with b(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
false,
false,
false
] | [
null,
null,
"Step 1: 96 * 9 = 864\nStep 2: 53 - 48 = 5\nStep 3: 864 + 5 = 869",
null
] | "[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED) | "[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED) | [
[],
[],
[
false
],
[]
] | [
[],
[],
[
"Step 1: 96 * 9 = 864\nStep 2: 53 - 48 = 5\nStep 3: 864 + 5 = 869"
],
[]
] | "[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8881, \"span_text\"(...TRUNCATED) | "[[], [], [{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 1: 96 * 9 = 864\(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 3,798 | 0 | 0 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I have the numbers: 48, 66, 47, 96, and 53. I need to use each exactly once with ba(...TRUNCATED) | [" maybe I can use parentheses to force order.\n\nFor example, (A * B) * (C / D) * (E / F), but that(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I have the numbers: 48, 66, 47, 96, and 53. I need to use each exactly once with b(...TRUNCATED) | [
false,
false
] | [null,"tags.\n\nAlso, for the single equation, I need to show the expression equal to 869.\n\nLet me(...TRUNCATED) | "[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED) | "[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED) | [
[],
[
false
]
] | [[],["tags.\n\nAlso, for the single equation, I need to show the expression equal to 869.\n\nLet me (...TRUNCATED) | "[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 9685, \"span_text\": \"(...TRUNCATED) | "[[], [{\"is_correct\": false, \"error\": \"Could not evaluate line: (96 * 53) / (48 * 1.375) = 5088(...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count":(...TRUNCATED) |
"Jim decides to go to college to earn some more money. It takes him 4 years to finish and he gets $(...TRUNCATED) | 4 | gsm8k | gsm8k | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"original_answer\": \"His salary increased to 25000*3=$<<25000*3=75000>>75,000 per year\\nSo he e(...TRUNCATED) | test | null | null | null | null | elementary_math | arithmetic_word_problems | numeric_equivalence | boxed_number | null | gsm8k_1038 | null | null | {} | "His salary increased to 25000*3=$<<25000*3=75000>>75,000 per year\nSo he earns an extra 75,000-25,0(...TRUNCATED) | gsm8k | math | test | null | null | ["<think>\nFirst, I need to understand the problem. Jim has two sources of income:\n\n1. A job with (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
false,
false,
true
] | [
"8",
"9",
"4 years",
"4"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 6, \"non_overlapping_spans\": 6, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"8\", \"correct_answer\": \"4(...TRUNCATED) | [
[
false,
false,
false,
false,
false,
false
],
[
false,
false
],
[
false
],
[
true
]
] | [
[
"8",
"8",
"8",
"(your answer)",
"49",
"8"
],
[
"(your answer)",
"9"
],
[
"4 years"
],
[
"4"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5587, \"span_text\": \"8\",(...TRUNCATED) | "[[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"8\", \"correct_answer\": \"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 6,712 | 1 | 1 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to understand the problem. Jim has two sources of income: before college, he(...TRUNCATED) | [" if Jim works part-time, he might be able to earn faster, but the problem does not specify such op(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to understand the problem. Jim has two sources of income: before college, h(...TRUNCATED) | [
false,
false
] | [
"9",
"9"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"9\", \"correct_answer\": \"4(...TRUNCATED) | [
[
false,
false
],
[
false,
false
]
] | [
[
"(your answer)",
"9"
],
[
"(your answer)",
"9"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3973, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"(your answer)\", \"correct_(...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"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) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"then\", \"words\": [\"classics\", \"oxford\", \"tweets\", \"healthy\", \"edinburgh\(...TRUNCATED) | test | then | null | null | null | null | null | null | null | then | null | null | null | {} | null | null | null | null | 7 | [
"classics",
"oxford",
"tweets",
"healthy",
"edinburgh",
"underwater",
"node"
] | ["<think>\nFirst, I need to understand the requirements for constructing an acronym based on the giv(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
false,
false,
false
] | [
null,
null,
null,
"cthsws"
] | "[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED) | "[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED) | [
[],
[],
[],
[
false,
false,
false
]
] | [
[],
[],
[],
[
"(your answer)",
"idea",
"cthsws"
]
] | "[[], [], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5030, \"span_te(...TRUNCATED) | "[[], [], [], [{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, i(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 11,828 | 0 | 0 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to understand the requirements for constructing an acronym based on the give(...TRUNCATED) | [" I need to create an acronym using the first letter of at least four words. The list has seven wor(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to understand the requirements for constructing an acronym based on the giv(...TRUNCATED) | [
false,
false
] | [
null,
"idea"
] | "[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non(...TRUNCATED) | "[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED) | [
[],
[
false,
false
]
] | [
[],
[
"idea",
"idea"
]
] | "[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 16540, \"span_text\": \(...TRUNCATED) | "[[], [{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_const(...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count":(...TRUNCATED) | |
787 x 997 | 784639 | longmult_3dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 787, \\\"arg2\\\": 997, \\\"solution\\\": 784639}\", \"task_source\(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | {"arg1": 787, "arg2": 997, "solution": 784639} | null | null | null | null | null | null | ["<think>\nFirst, I need to multiply 787 and 997. The numbers are both large, so I should use estima(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
true,
true,
false,
false
] | [
"784639",
"784639",
null,
"(your answer)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [
[
false,
false,
true
],
[
false,
true,
false,
false,
true
],
[],
[
true,
false
]
] | [["(your answer)","(your answer)","784639"],["(your answer)","784639","(your answer)","(your answer)(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1944, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,1,0,1],"flips_total":2,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED) | 9,097 | 1 | 1 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to multiply 787 and 997. The numbers are both large, so I should use the sta(...TRUNCATED) | [" In the given options, the problem might require the answer in a specific format, but based on the(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to multiply 787 and 997. The numbers are both large, so I should use the st(...TRUNCATED) | [
true,
true
] | [
"784639",
"784639"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [
[
false,
true,
false,
false,
true
],
[
false,
true,
false,
false,
true
]
] | [["(your answer)","784639","(your answer)","(your answer)","784639"],["(your answer)","784639","(you(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1290, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[1,1],"flips_total":2,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED) |
8314 x 4491 | 37338174 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 8314, \\\"arg2\\\": 4491, \\\"solution\\\": 37338174}\", \"task_sou(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | {"arg1": 8314, "arg2": 4491, "solution": 37338174} | null | null | null | null | null | null | ["<think>\nFirst, I need to multiply these two numbers: 8314 and 4491. Let me start with the first d(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
true,
false,
false
] | [
"37487826",
"37338174",
"17",
"37404686"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [
[
false,
false,
false,
false
],
[
true,
true
],
[
false,
false
],
[
false,
false
]
] | [["...","37487826","(your answer)","37487826"],["37338174","37338174"],["(your answer )","17"],["374(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4057, \"span_text\": \"...\(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 9,909 | 1 | 1 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to multiply 8314 by 4491. Let me start with the multiplication of these two (...TRUNCATED) | [" In the instruction, it says \"give your answer in this format\": <answer>(your answer)</answer>. (...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to multiply 8314 by 4491. Let me start with the multiplication of these two(...TRUNCATED) | [
true,
true
] | [
"37338174",
"37338174"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [
[
true,
true
],
[
true,
false,
true
]
] | [
[
"37338174",
"37338174"
],
[
"37338174",
"(your answer)",
"37338174"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4608, \"span_text\": \"3733(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | {"flips_by":[0,1],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":1.0,"skill_count":(...TRUNCATED) |
"Fern is trying to decide between buying the Widgeteer 3000, which makes 60 widgets an hour, and the(...TRUNCATED) | 64800 | gsm8k | gsm8k | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"original_answer\": \"First find how many more widgets the Widgeteer 3000 makes per hour: 60 widg(...TRUNCATED) | test | null | null | null | null | elementary_math | arithmetic_word_problems | numeric_equivalence | boxed_number | null | gsm8k_935 | null | null | {} | "First find how many more widgets the Widgeteer 3000 makes per hour: 60 widgets/hour - 45 widgets/ho(...TRUNCATED) | gsm8k | math | test | null | null | ["<think>\nFirst, I need to calculate how many widgets each machine can produce in one hour and then(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | "{\"api_url\": \"http://127.0.0.1:41869/v1\", \"backend\": \"litellm\", \"chat_template_applied\": t(...TRUNCATED) | "{\"backend\": \"litellm\", \"model_name\": \"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_o(...TRUNCATED) | 2025-09-24 | [
false,
true,
false,
false
] | [
"$64800",
"64800",
"$64,800",
"6480"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"$64800\", \"correct_answer\"(...TRUNCATED) | [
[
false
],
[
true
],
[
false,
false,
false,
false,
false
],
[
false
]
] | [
[
"$64800"
],
[
"64800"
],
[
"(your answer)",
"(your answer)",
"(your answer)",
"259200",
"$64,800"
],
[
"6480"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3631, \"span_text\": \"$648(...TRUNCATED) | "[[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"$64800\", \"correct_answer\(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 6,579 | 2 | 2 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | "<think>\nFirst, I need to calculate how many widgets each machine can produce in a month with 24 ho(...TRUNCATED) | [" the problem mentions \"each widget sells for $6,\" implying the price remains consistent regardle(...TRUNCATED) | [
false
] | [
""
] | {"api_url":"http://127.0.0.1:50597","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | ["<think>\nFirst, I need to calculate how many widgets each machine can produce in a month with 24 h(...TRUNCATED) | [
false,
true
] | [
"$64,800",
"64800"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"$64,800\", \"correct_answer\(...TRUNCATED) | [
[
false,
false,
false,
false,
false
],
[
false,
false,
false,
false,
true
]
] | [["(your answer)","(your answer)","(your answer)","259200","$64,800"],["(your answer)","(your answer(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1797, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"math_equivalence\", \"extracted_answer\": \"(your answer)\", \"correct_(...TRUNCATED) | {"flips_by":[0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.5,"skill_count":(...TRUNCATED) |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 1