data_source stringclasses 4
values | prompt listlengths 2 2 | ability stringclasses 3
values | reward_model dict | domain stringclasses 3
values | extra_info dict |
|---|---|---|---|---|---|
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-42804",
"instruction_id_list": [
"length_constraints:number_sentences",
"length_constraints:number_words",
"keywords:no_adjacent_conse... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-3622",
"instruction_id_list": [
"length_constraints:nth_paragraph_first_word",
"count:count_increment_word"
],
"instruction_kwargs_json": [
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4\\n3 2\\n3 1\\n8 6\\n8 7 6 5 3 2\\n9 6\\n9 8 5 4 3 1\\n1 1\\n1\\n\", \"output\": \"0\\n1\\n2\\n0\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n3 2\\n3 2\\n\", \"output\": \"1\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"28\\n8 4\\n8 7 6 3\\n8 5... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-13060",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 13060,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "13060",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "16",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-8286",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 8286,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "78194331-a627-43f2-8df7-816eda1e2290",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-17610",
"instruction_id_list": [
"punctuation:no_comma",
"detectable_format:number_bullet_lists",
"detectable_format:sentence_hyphens"
],
"inst... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"function_call\", \"fn_name\": \"pillow\", \"input\": [[\"EvH/KNikBiyxfeyK/miCMj\", \"I/HwjnHlFLlahMOKNadps\"]], \"output\": [false]}, {\"type\": \"function_call\", \"fn_name\": \"pillow\", \"input\": [[\"\\\\DjQ\\\\[zv]SpG]Z/[Qm\\\\eLL\", \"amwZArsaGRmibriXBgTRZp\"]], \"output\": [fal... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-23491",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 23491,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "23491",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "719",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-6366",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 6366,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "578d78cc-147e-4951-9cdf-81c1be76d80e",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-23466",
"instruction_id_list": [
"keywords:palindrome"
],
"instruction_kwargs_json": [
"null"
],
"mix_index": 23466,
"raw_prompt": "I helped ... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4\\nhoge\\nenglish\\nhoge\\nenigma\", \"output\": \"No\"}, {\"type\": \"stdin_stdout\", \"input\": \"9\\nbasic\\nc\\ncpp\\nphp\\npython\\nnadesico\\nocaml\\nlua\\nassembly\", \"output\": \"Yes\"}, {\"type\": \"stdin_stdout\", \"input\": \"3\\nabc\\narc\\na... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-16437",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 16437,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "16437",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "34",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-17267",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 17267,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "2fbcde3a-bc59-4251-adca-9c550bed39d6",
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "12",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-13649",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 13649,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "16301d1f-b7bc-47fc-bccf-e72718a01618",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"3\\n\", \"output\": \"0 3 4\\n3 0 5\\n4 5 0\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"17\\n\", \"output\": \"0 3 4 6 9 14 22 31 40 54 75 96 129 153 183 213 259\\n3 0 5 7 10 15 23 32 41 55 76 97 130 154 184 214 260\\n4 5 0 8 11 16 24 33 42 56 77 98 1... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-13339",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 13339,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "13339",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-38938",
"instruction_id_list": [
"combination:two_responses",
"punctuation:no_comma"
],
"instruction_kwargs_json": [
"null",
"null"
],
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-7736",
"instruction_id_list": [
"keywords:start_end",
"first_word:first_word_sent"
],
"instruction_kwargs_json": [
"null",
"{\"first_word\"... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-8715",
"instruction_id_list": [
"detectable_format:sentence_hyphens"
],
"instruction_kwargs_json": [
"null"
],
"mix_index": 8715,
"raw_prompt... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-44375",
"instruction_id_list": [
"change_case:english_lowercase",
"length_constraints:nth_paragraph_first_word"
],
"instruction_kwargs_json": [
... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"1\\n2\\n3\\n390\\n216\\n1546\\n314159265358979323\\n0\", \"1\\n2\\n2\\n390\\n1124\\n1546\\n314159265358979323\\n0\", \"1\\n2\\n3\\n390\\n216\\n1546\\n31125328462643205\\n0\", \"1\\n2\\n2\\n390\\n1124\\n1546\\n211760204581026131\\n0\", \"1\\n2\\n3\\n104\\n216\\n1546\\n311253284626432... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-6558",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 6558,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "6558",
"split": "train"
} |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"8\\nkamusta_po\\ngenki_desu\\nohayou_gozaimasu\\nannyeong_hashimnida\\nhajime_no_ippo\\nbensamu_no_sentou_houhou_ga_okama_kenpo\\nang_halaman_doon_ay_sarisari_singkamasu\\nsi_roy_mustang_ay_namamasu\\n\", \"output\": \"FILIPINO\\nJAPANESE\\nJAPANESE\\nKORE... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-10905",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 10905,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "10905",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "count_or_pattern",
"index": "if-27102",
"instruction_id_list": [
"keywords:word_count_different_numbers",
"last_word:last_word_answer",
"detectable_content:postscript"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-23128",
"instruction_id_list": [
"length_constraints:number_paragraphs",
"change_case:english_capital"
],
"instruction_kwargs_json": [
"{\"n... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-960",
"instruction_id_list": [
"punctuation:punctuation_dot",
"keywords:existence"
],
"instruction_kwargs_json": [
"null",
"{\"keywords\... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-1393",
"instruction_id_list": [
"last_word:last_word_sent",
"count:count_increment_word"
],
"instruction_kwargs_json": [
"{\"last_word\": \"... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-20263",
"instruction_id_list": [
"length_constraints:number_sentences",
"change_case:capital_word_frequency",
"keywords:keyword_specific_positio... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"3\\n0709\\n1337\\n246432\\n\", \"output\": \"0079\\n1337\\n234642\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n1003\\n\", \"output\": \"0013\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n890\\n\", \"output\": \"809\\n\"}, {\"type\": \"stdin_... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-10788",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 10788,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "10788",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-44174",
"instruction_id_list": [
"count:counting_composition",
"change_case:english_lowercase"
],
"instruction_kwargs_json": [
"{\"n_sent\":... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-4818",
"instruction_id_list": [
"keywords:letter_frequency",
"length_constraints:nth_paragraph_first_word",
"detectable_format:number_... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-14366",
"instruction_id_list": [
"detectable_format:bigram_wrapping",
"change_case:english_lowercase",
"length_constraints:number_paragraphs"
... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"12 1 5 10\\n3 5 6 7 8 9 5 1 1 1 1 5\\n\", \"3 2 1 2\\n6 2 2\\n\", \"3 2 1 2\\n3 1 2\\n\", \"3 2 1 2\\n6 3 2\\n\", \"3 2 1 2\\n3 6 3\\n\", \"3 2 0 2\\n3 3 9\\n\", \"3 2 0 2\\n4 5 1\\n\", \"3 2 0 2\\n1 3 2\\n\", \"3 2 1 2\\n5 9 3\\n\", \"3 2 1 2\\n7 2 4\\n\", \"6 5 2 12\\n2 8 9 6 6 1\... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-1150",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1150,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "1150",
"split": "train"
} |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-1949",
"instruction_id_list": [
"length_constraints:number_words",
"keywords:keyword_specific_position"
],
"instruction_kwargs_json": [
"{\"... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "328",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-2831",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 2831,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "b2add6ae-8812-43f8-b152-c5ed95f68451",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "detectable_format",
"index": "if-3067",
"instruction_id_list": [
"last_word:last_word_sent",
"count:counting_composition",
"copy:repeat_phrase"
],
"instruction_kwar... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"sardine\", \"output\": \"xxxxxxx\"}, {\"type\": \"stdin_stdout\", \"input\": \"xxxx\", \"output\": \"xxxx\"}, {\"type\": \"stdin_stdout\", \"input\": \"gone\", \"output\": \"xxxx\"}, {\"type\": \"stdin_stdout\", \"input\": \"sardnie\", \"output\": \"xxxxxx... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-16705",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 16705,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "16705",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "26",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-15372",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 15372,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "d222aff0-d8fc-4681-81bc-697d72bc3564",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4\\n3876\\n387\\n4489\\n3\\n\", \"output\": \"0\\n2\\n1\\n-1\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n99\\n\", \"output\": \"-1\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n841419\\n\", \"output\": \"1\\n\"}, {\"type\": \"stdin_stdout\"... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-22996",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 22996,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "22996",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-44255",
"instruction_id_list": [
"letters:letter_counting2",
"count:lowercase_counting",
"paragraphs:paragraphs2"
],
"instruction_... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-2817",
"instruction_id_list": [
"detectable_format:title",
"keywords:existence"
],
"instruction_kwargs_json": [
"null",
"{\"keywords\": ... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4 1 4\\n3 2 2 2\", \"output\": \"7\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"6 2 2\\n1 2 2 2 2 0\", \"output\": \"6\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"8 7 15\\n5 0 9 14 0 4 0 15\", \"output\": \"217\\n\"}, {\"type\": \"stdin_stdout\", ... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-21634",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 21634,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "21634",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-17704",
"instruction_id_list": [
"keywords:palindrome",
"keywords:word_once"
],
"instruction_kwargs_json": [
"null",
"{\"keyword\": \"he... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"3\\n0\\n2\\n1073741823\\n\", \"output\": \"1\\n2\\n1073741824\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"9\\n2\\n2\\n8\\n228\\n1\\n4\\n8\\n8\\n1488\\n\", \"output\": \"2\\n2\\n2\\n16\\n2\\n2\\n2\\n2\\n32\\n\"}, {\"type\": \"stdin_stdout\", \"input\":... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-11303",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 11303,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "11303",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "23",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-13746",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 13746,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "1ff784df-3e4f-4ef4-b5d8-f6e48126593e",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "count_or_pattern",
"index": "if-44125",
"instruction_id_list": [
"length_constraints:nth_paragraph_first_word",
"keywords:palindrome"
],
"instruction_kwargs_json": [
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-17485",
"instruction_id_list": [
"first_word:first_word_answer",
"keywords:palindrome",
"punctuation:no_comma"
],
"instruction_kwargs_json": [
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-37388",
"instruction_id_list": [
"change_case:english_lowercase",
"first_word:first_word_sent"
],
"instruction_kwargs_json": [
"null",
"... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-26370",
"instruction_id_list": [
"change_case:english_lowercase",
"detectable_format:square_brackets",
"keywords:letter_frequency"
],
"instr... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"function_call\", \"fn_name\": \"get_score\", \"input\": [[1]], \"output\": [100]}, {\"type\": \"function_call\", \"fn_name\": \"get_score\", \"input\": [[5]], \"output\": [50]}, {\"type\": \"function_call\", \"fn_name\": \"get_score\", \"input\": [[1, 1]], \"output\": [200]}, {\"type\... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-22094",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 22094,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "22094",
"split": "train"
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"0101\\n1101001\", \"output\": \"0000\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"0101\\n1100000\", \"output\": \"111\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"0101\\n1101000\", \"output\": \"0001\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-18673",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 18673,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "18673",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-30932",
"instruction_id_list": [
"change_case:english_lowercase",
"punctuation:punctuation_exclamation",
"length_constraints:number_paragraphs"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-22227",
"instruction_id_list": [
"letters:letter_counting",
"length_constraints:number_paragraphs",
"change_case:english_lowercase"
],
"inst... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "40003",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-3012",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 3012,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "202b27f8-5cbe-43b2-9502-dd01826b5279",
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "112",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-14914",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 14914,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "e8126131-4531-4695-8fa0-eb638beda2f2",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-38142",
"instruction_id_list": [
"count:count_unique",
"keywords:keyword_specific_position"
],
"instruction_kwargs_json": [
"null",
"{\"... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"05:39\\n\", \"13:31\\n\", \"23:59\\n\", \"13:32\\n\", \"14:40\\n\", \"14:00\\n\", \"05:50\\n\", \"12:22\\n\", \"12:34\\n\", \"05:30\\n\", \"14:14\\n\", \"01:10\\n\", \"02:20\\n\", \"03:30\\n\", \"04:40\\n\", \"10:01\\n\", \"11:11\\n\", \"12:21\\n\", \"14:41\\n\", \"15:51\\n\", \"20:... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-6646",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 6646,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "6646",
"split": "train"
} |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4\\nXOOO\\nXXOO\\nOOOO\\nXXXX\\nXOOO\\nXOOO\\nXOXO\\nXOXX\\n\", \"output\": \"Yes\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"2\\nXX\\nOO\\nXO\\nOX\\n\", \"output\": \"No\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\nO\\nO\\n\", \"output\": \"Y... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-8213",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 8213,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "8213",
"split": "train"
} |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "detectable_format",
"index": "if-19204",
"instruction_id_list": [
"detectable_format:title",
"punctuation:no_comma"
],
"instruction_kwargs_json": [
"null",
"nul... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-15877",
"instruction_id_list": [
"punctuation:no_comma",
"copy:repeat_phrase"
],
"instruction_kwargs_json": [
"null",
"{\"phrase\": \"The p... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"20 30\", \"output\": \"0\"}, {\"type\": \"stdin_stdout\", \"input\": \"12 4\", \"output\": \"4\"}, {\"type\": \"stdin_stdout\", \"input\": \"20 15\", \"output\": \"0\"}, {\"type\": \"stdin_stdout\", \"input\": \"27 30\", \"output\": \"0\\n\"}, {\"type\": \... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-16651",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 16651,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "16651",
"split": "train"
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "288",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-12033",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 12033,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "988d6afa-19e3-408d-87f8-eb0f42f44a54",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"3\\n13 7 6\\n6 2\\n\", \"output\": \"4\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n999999999\\n499999999 1\\n\", \"output\": \"1\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"10\\n1 10 100 1000 10000 100000 1000000 10000000 100000000 1000000000... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-16099",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 16099,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "16099",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-37806",
"instruction_id_list": [
"change_case:english_lowercase",
"detectable_format:bigram_wrapping",
"detectable_format:sentence_hyphens"
],... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-24242",
"instruction_id_list": [
"language:response_language",
"first_word:first_word_sent",
"paragraphs:paragraphs2"
],
"instruction_kwargs... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "32",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-9875",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 9875,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "c024b94d-0f90-47ec-8389-86514c889101",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-41834",
"instruction_id_list": [
"detectable_format:bigram_wrapping",
"detectable_format:number_bullet_lists"
],
"instruction_kwargs_json": [
"... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "706",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-483",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 483,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "6f79e419-acfa-4956-b510-b1e891a50a6a",
"s... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "51",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-15171",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 15171,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "160f17e1-da11-4324-870e-ff861d3b3a53",
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "29",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-4755",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 4755,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "a64b4b50-8885-4f37-ae6d-e7c3d60ee92d",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-42595",
"instruction_id_list": [
"letters:letter_counting2",
"last_word:last_word_sent"
],
"instruction_kwargs_json": [
"{\"let_fr... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-22339",
"instruction_id_list": [
"copy:repeat_phrase",
"keywords:frequency"
],
"instruction_kwargs_json": [
"{\"phrase\": \"Time f... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"2\\naaab\\n\", \"2\\nbabac\\n\", \"2\\naaaaaabbbb\\n\", \"1\\naabaab\\n\", \"2\\naabbbbccccccdddddddd\\n\", \"2\\nabba\\n\", \"2\\naaaazzzz\\n\", \"250\\ncecececececececececececececececececececececececececececececececececececececececececececececececececececececececececececececececec... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-1647",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1647,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "1647",
"split": "train"
} |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "64",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-9428",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 9428,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "905aaa6e-1b9f-4c98-bdc4-5cbf1684413f",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"6 2 1 2\\n\", \"output\": \"6\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"5 2 2 3\\n\", \"output\": \"8\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"10 3 5 1\\n\", \"output\": \"4\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1000 1 1000 1000\\... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-8734",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 8734,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "8734",
"split": "train"
} |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"3 20\\n5\\n11\\n3\", \"3 20\\n5\\n11\\n6\", \"3 20\\n1\\n11\\n6\", \"3 20\\n1\\n3\\n6\", \"3 20\\n1\\n3\\n3\", \"3 25\\n1\\n3\\n3\", \"3 35\\n1\\n3\\n3\", \"3 35\\n1\\n3\\n4\", \"3 55\\n1\\n3\\n4\", \"3 55\\n1\\n3\\n0\", \"3 55\\n1\\n4\\n0\", \"3 55\\n2\\n4\\n0\", \"3 20\\n7\\n7\\n3... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-1935",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1935,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "1935",
"split": "train"
} |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-892",
"instruction_id_list": [
"change_case:english_capital",
"detectable_format:bigram_wrapping",
"length_constraints:nth_paragraph_first_word"... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-32633",
"instruction_id_list": [
"first_word:first_word_sent",
"keywords:start_end"
],
"instruction_kwargs_json": [
"{\"first_word\": \"cancer\... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-39798",
"instruction_id_list": [
"detectable_format:number_highlighted_sections",
"first_word:first_word_answer",
"length_constraints:... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "340",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-8499",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 8499,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "c70db718-413a-4584-bd8e-9fbc70f9c1a8",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"21\\n\", \"output\": \"1\\n15\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"20\\n\", \"output\": \"0\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n\", \"output\": \"0\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"2\\n\", \"output\": \"1\\n1\\n... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-7446",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 7446,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "7446",
"split": "train"
} |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-32536",
"instruction_id_list": [
"detectable_content:number_placeholders",
"detectable_format:number_bullet_lists"
],
"instruction_kwa... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "30000",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-3335",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 3335,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "b09321ad-4ece-45f1-b6c7-9fd1c0e5096e",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"10\\n10\", \"output\": \"76\"}, {\"type\": \"stdin_stdout\", \"input\": \"4\\n3\", \"output\": \"10\"}, {\"type\": \"stdin_stdout\", \"input\": \"10\\n17\", \"output\": \"117\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"4\\n4\", \"output\": \"12\\n\"},... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-12224",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 12224,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "12224",
"split": "train"
... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"5\\n2 1 3 4 5\\n3 4 2 5 1\", \"5\\n1 2 3 4 5\\n2 4 3 5 1\", \"5\\n1 3 2 4 5\\n3 4 2 5 1\", \"5\\n2 1 3 4 5\\n2 4 3 5 1\", \"5\\n1 4 3 2 5\\n3 4 2 5 1\", \"5\\n2 1 3 4 5\\n3 4 2 5 1\", \"5\\n1 2 3 4 5\\n2 4 3 5 1\", \"5\\n2 1 3 4 5\\n3 4 1 5 2\", \"5\\n1 4 3 2 5\\n3 4 1 5 2\", \"5\\n... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-3595",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 3595,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "3595",
"split": "train"
} |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-26646",
"instruction_id_list": [
"detectable_format:constrained_response"
],
"instruction_kwargs_json": [
"null"
],
"mix_index": 26646,
"raw_... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "other",
"index": "if-24304",
"instruction_id_list": [
"detectable_format:number_bullet_lists",
"detectable_format:sentence_hyphens"
],
"instruction_kwargs_json": [
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "detectable_format",
"index": "if-22924",
"instruction_id_list": [
"length_constraints:number_sentences",
"count:counting_composition",
"detectable_format:title"
],
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-16677",
"instruction_id_list": [
"language:response_language",
"punctuation:no_comma",
"change_case:capital_word_frequency"
],
"instruction_... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "1004",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-4646",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 4646,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "a0828051-808d-461e-acf0-7e4a1636419d",
... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"4\\n0 0\\n3 1\\n2 3\\n0 3\\n3\\n2 1\\n0 2\\n0 2\", \"4\\n0 0\\n3 0\\n2 3\\n0 1\\n3\\n2 1\\n0 2\\n0 2\", \"4\\n0 -1\\n3 1\\n2 3\\n0 3\\n1\\n2 1\\n0 2\\n3 1\", \"4\\n0 -1\\n2 1\\n2 3\\n0 3\\n1\\n2 1\\n0 1\\n3 1\", \"4\\n0 -1\\n3 0\\n3 2\\n1 3\\n1\\n0 2\\n1 0\\n0 1\", \"4\\n0 -1\\n6 -2... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-2522",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 2522,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "2522",
"split": "train"
} |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"function_call\", \"fn_name\": \"prime_or_composite\", \"input\": [2], \"output\": [\"Probable Prime\"]}, {\"type\": \"function_call\", \"fn_name\": \"prime_or_composite\", \"input\": [3], \"output\": [\"Probable Prime\"]}, {\"type\": \"function_call\", \"fn_name\": \"prime_or_composit... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-19660",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 19660,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "19660",
"split": "train"
... |
taco | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "{\"inputs\": [\"23\\n1 1 1\\n2 2 1\", \"23\\n1 2 1\\n2 1 1\", \"23\\n1 2 1\\n2 0 1\", \"23\\n0 2 1\\n2 0 1\", \"23\\n1 1 2\\n1 1 0\", \"23\\n1 1 1\\n2 0 1\", \"23\\n1 4 1\\n2 1 1\", \"23\\n1 1 2\\n2 3 0\", \"23\\n0 2 1\\n4 0 1\", \"23\\n1 8 1\\n2 1 1\", \"23\\n0 2 1\\n1 0 1\", \"23\\n1 1 2\\n2 0 0\... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-4750",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 4750,
"raw_prompt": null,
"sample_id": null,
"source_config": "taco",
"source_index": "4750",
"split": "train"
} |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "55",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-1852",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1852,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "45b85769-ff2b-45d1-a877-840c2e9f9344",
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "length_constraints",
"index": "if-3893",
"instruction_id_list": [
"keywords:letter_frequency",
"count:count_unique",
"detectable_format:sentence_hyphens"
],
"instru... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-39853",
"instruction_id_list": [
"keywords:word_once",
"punctuation:punctuation_dot"
],
"instruction_kwargs_json": [
"{\"keyword\": \"major\... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "184320",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-1096",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1096,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "70020761-9346-4988-b649-551bb383b774",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"1098\\n\", \"output\": \"20\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"10\\n\", \"output\": \"19\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1000000000\\n\", \"output\": \"91\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"1\\n\", \"output\": \... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-9802",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 9802,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "9802",
"split": "train"
} |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "47",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-7150",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 7150,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "b2089333-c94c-4f71-8fe5-3715f9195ca9",
... |
math_dapo_boxed | [
{
"content": "You are an expert mathematical problem solver. Solve the problem carefully. You must first show all your step-by-step reasoning and derivations inside <think> and </think> tags. After your thought process, provide the final answer clearly and make it easy to verify.",
"role": "system"
},
{... | MATH | {
"ground_truth": "1656",
"style": "rule"
} | math | {
"agent_name": null,
"dataset": null,
"domain": "math",
"family": null,
"index": "math-1766",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 1766,
"raw_prompt": null,
"sample_id": null,
"source_config": null,
"source_index": "a0127ade-6703-450c-983c-7559dd39e5ff",
... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"2\\n9\\n0\", \"output\": \"5\\n100\"}, {\"type\": \"stdin_stdout\", \"input\": \"2\\n2\\n0\", \"output\": \"5\\n5\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"2\\n17\\n0\", \"output\": \"5\\n440\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"2\\n7\\n... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-12450",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 12450,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "12450",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "keywords",
"index": "if-6345",
"instruction_id_list": [
"detectable_format:json_format",
"keywords:forbidden_words"
],
"instruction_kwargs_json": [
"null",
"{\"... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "language",
"index": "if-40074",
"instruction_id_list": [
"punctuation:punctuation_dot",
"length_constraints:number_words",
"change_case:english_lowercase"
],
"instr... |
primeintellect | [
{
"content": "You are an expert programmer and competitive problem solver. Solve the task carefully. You must first outline your thought process, logic, and planning inside <think> and </think> tags, and then produce a correct final implementation outside of these tags.",
"role": "system"
},
{
"cont... | code | {
"ground_truth": "[{\"type\": \"stdin_stdout\", \"input\": \"4\\n1 1 1 1\\n\", \"output\": \"15\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"4\\n2 2 2 2\\n\", \"output\": \"7\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"5\\n1 2 4 5 8\\n\", \"output\": \"7\\n\"}, {\"type\": \"stdin_stdout\", \"input\": \"10\\... | code | {
"agent_name": null,
"dataset": null,
"domain": "code",
"family": null,
"index": "code-16755",
"instruction_id_list": null,
"instruction_kwargs_json": null,
"mix_index": 16755,
"raw_prompt": null,
"sample_id": null,
"source_config": "primeintellect",
"source_index": "16755",
"split": "train"
... |
nemotron_if_rl | [
{
"content": "You are an expert general-purpose assistant. Follow every user instruction exactly, especially formatting, wording, ordering, and length constraints. You must always begin your response with exactly <think>\n</think> (a single newline inside the tags), and then immediately provide your answer.",
... | instruction_following | {
"ground_truth": "",
"style": "rule"
} | if | {
"agent_name": "instruction_following_simple_agent",
"dataset": "nano-v3-RL-instruction_following",
"domain": "if",
"family": "detectable_format",
"index": "if-40857",
"instruction_id_list": [
"length_constraints:nth_paragraph_first_word",
"count:counting_composition",
"first_word:first_word_an... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.