Datasets:
id int64 | responses_create_params unknown | ground_truth list | category string | environment_name string | agent_ref dict | pass_rate float64 | pass_rate_total int64 | pass_rate_passed int64 | dataset string | kwargs list | options list | _hf_placeholder dict | expected_answer string | uuid string | reward_profiles list | template_metadata dict | instruction_id_list list | prompt string | verifier_metadata dict | hash_id string | source string | schema_str string | schema_type string | schema_fields_count string |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
317 | {
"input": [
{
"role": "system",
"content": "Today's date is Thursday, 2023-11-30 and the current time is 23:59:00. Remember the current date and time when answering queries. Meetings must not start before 9am or end after 6pm."
},
{
"role": "user",
"content": "kofi just sent me an... | [
{
"name": "email_delete_email",
"arguments": "{\"email_id\": \"00000259\"}"
}
] | workbench_email | workbench | {
"type": "responses_api_agents",
"name": "workplace_assistant_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_workbench | null | null | null | null | null | null | null | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: \\boxed{A/B/C/D/E/F/G/H/I/J}' (e.g. 'Answer: \\boxed{C}').\n\nIn a prosecution for criminal contempt arising from the termination of a pr... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.5 | 8 | 4 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "The failure to define “willfully” deprived the jury of a clear standard for criminal intent."
},
{
"B": "The prosecution did not introduce sufficient evidence that the utility shutoff caused emotional distress."
},
{
"C": "The defendant had a reasonable belief that the utilities were shu... | null | F | bf663b95-466a-5452-b613-f86ff62edcf6 | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 1
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0
}
] | {
"template_id": "mcqa_benchmark_001",
"template_prompt": "Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: \\boxed{{A/B/C/D}}' (e.g. 'Answer: \\boxed{{A}}').\n\n{problem}",
"output_regex": "\\\\boxed\\{\\s*([A-Za-z0-9])\\s*\\}",
"weight":... | null | null | null | null | null | null | null | null |
15,751 | {
"input": [
{
"role": "user",
"content": "Please follow these instructions in your response: In your response, words with all capital letters should appear at least 6 times and In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Christian Vaughn ... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0 | 8 | 0 | nano_v3_sft_profiled_instruction_following | [
{
"capital_frequency": 6,
"capital_relation": "at least"
},
null
] | null | null | null | null | null | null | [
"change_case:capital_word_frequency",
"punctuation:punctuation_exclamation"
] | Please follow these instructions in your response: In your response, words with all capital letters should appear at least 6 times and In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Christian Vaughn is the main character of this fighting game similar to Def Ja... | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.625 | 8 | 5 | nano_v3_sft_profiled_dapo17k | null | null | {
"row": 1779945,
"question_template": "\"{\\\"prefix\\\":\\\"\\\",\\\"suffix\\\":\\\"Don't forget to put your answer in \\\\\\\\boxed{}.\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"10000\n5000 3150\n5000 5000\n0 0\n5000 1050\n5000 3980\n5000 210\n5000 5000\n5000 5000\n0 0\n5000 2100\n5000 2100\n5000 2100\n29170\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 100000\n100000 10... | d33eaf0eb9ec3c1de407af5b5afa6c14 | aizu | null | null | null |
null | {
"input": [
{
"content": "# Instrutions:\nGenerate a JSON output that strictly adheres to the specified schema based on the document provided.\n\n# Document:\nThe individual has established clear financial goals across short-, medium-, and long-term horizons. The short-term goal is to build a fully funded ... | null | null | null | {
"type": "responses_api_agents",
"name": "structured_outputs_simple_agent"
} | 0.375 | 8 | 3 | nano_v3_sft_profiled_structured_outputs | null | null | null | null | null | null | null | null | null | null | null | null | {"type": "object", "properties": {"financialGoals": {"type": "object", "properties": {"shortTerm": {"type": "string"}, "mediumTerm": {"type": "string"}, "longTerm": {"type": "string"}}, "required": ["shortTerm", "mediumTerm", "longTerm"], "additionalProperties": false}, "monthlyIncome": {"type": "number"}, "monthlyExpe... | json | 12 |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"5\n0 1 3 6 10\n3 10\n2 3 4",
"5\n0 1 3 6 17\n3 10\n3 3 4",
"5\n0 1 3 6 17\n3 1\n3 3 4",
"3\n1 -1 1\n2 3\n2 2",
"5\n0 1 3 6 9\n3 10\n2 3 4",
"3\n0 0 1\n2 2\n2 2",
"5\n0 1 3 11 17\n3 1\n3 3 4",
"3\n0 0 2\n2 2\n2 2",
"3\n1 -1 2\n2 2... | b445b18fae81f5b7e205bbe153420786 | atcoder | null | null | null |
22,679 | {
"input": [
{
"role": "user",
"content": "Make sure to follow these requirements when responding:\n1. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***\n2. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.\n3. Include keyword [... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0 | 8 | 0 | nano_v3_sft_profiled_instruction_following | [
{},
{
"num_highlights": 3
},
{
"keyword1": [
"lake"
],
"keyword2": [
"comfort"
]
}
] | null | null | null | null | null | null | [
"paragraphs:paragraphs",
"detectable_format:number_highlighted_sections",
"count:count_increment_word"
] | Make sure to follow these requirements when responding:
1. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***
2. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.
3. Include keyword ['lake'] once in your response, keyword ['comfort'] twice in your... | null | null | null | null | null | null |
4,084 | {
"input": [
{
"role": "user",
"content": "Your response should satisfy these conditions:\n1. The response must contain at least 3 placeholders represented by square brackets, such as [address].\n2. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***\n\nSuponha como s... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_instruction_following | [
{
"num_placeholders": 3
},
{}
] | null | null | null | null | null | null | [
"detectable_content:number_placeholders",
"paragraphs:paragraphs"
] | Your response should satisfy these conditions:
1. The response must contain at least 3 placeholders represented by square brackets, such as [address].
2. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***
Suponha como seria para os humanos e para animais marinhos e fluviais se o ocea... | null | null | null | null | null | null |
null | {
"input": [
{
"content": "Format your response as a JSON object adhering to:\n- Schema structure: {\"type\": \"object\", \"required\": [\"articleId\", \"title\", \"privacyImpactAssessment\", \"published\", \"source\"], \"properties\": {\"articleId\": {\"type\": \"string\", \"description\": \"Unique identif... | null | null | null | {
"type": "responses_api_agents",
"name": "structured_outputs_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_structured_outputs | null | null | null | null | null | null | null | null | null | null | null | null | {"type": "object", "required": ["articleId", "title", "privacyImpactAssessment", "published", "source"], "properties": {"articleId": {"type": "string", "description": "Unique identifier for the news article"}, "title": {"type": "string", "description": "Headline or title of the news article"}, "published": {"type": "bo... | json | 5 |
45,987 | {
"input": [
{
"role": "user",
"content": "Please follow these instructions in your response: In your response, the word spiritual should appear 2 times and In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Ben eczacıyım. Hastam siklosporin 100 mg tabletten ... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.625 | 8 | 5 | nano_v3_sft_profiled_instruction_following | [
{
"keyword": "spiritual",
"frequency": 2,
"relation": "at least"
},
null
] | null | null | null | null | null | null | [
"keywords:word_count_different_numbers",
"punctuation:punctuation_dot"
] | Please follow these instructions in your response: In your response, the word spiritual should appear 2 times and In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Ben eczacıyım. Hastam siklosporin 100 mg tabletten günde 2 defa alıyor. Aç veya tok karna alması fark eder mi? | null | null | null | null | null | null |
14,371 | {
"input": [
{
"role": "user",
"content": "finereport下载网站\n\nMake sure to adhere to these requirements:\n- In your response, words with all capital letters should appear at least 16 times.\n- Start and end your response with the same word (do not write anything after the last word, not even punctuatio... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_instruction_following | [
{
"capital_frequency": 16,
"capital_relation": "at least"
},
null
] | null | null | null | null | null | null | [
"change_case:capital_word_frequency",
"keywords:start_end"
] | finereport下载网站
Make sure to adhere to these requirements:
- In your response, words with all capital letters should appear at least 16 times.
- Start and end your response with the same word (do not write anything after the last word, not even punctuation). | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "After Pam accepted the (erroneous) $20,000 offer and Matz said \"Done,\" Matz began constructing the press and completed 40% before Pam notified him she would not take delivery. If Matz sues for breach of contract, which of the following is most accurate unde... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "Matz cannot recover because no enforceable contract exists."
},
{
"B": "Matz may recover only out-of-pocket costs incurred."
},
{
"C": "Matz may recover the full contract price as damages."
},
{
"D": "Matz may recover reliance damages or lost profits under promissory estoppel."
... | null | G | 2b2b0a11-ef2b-598d-9112-ae4670661e4a | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 1
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0
}
] | {
"template_id": "mcqa_generated_119",
"template_prompt": "{problem}\n\nProvide your final answer at the end of the response, enclosed in single angle brackets as follows: <X>.\n\nConsider the following question carefully and select the most appropriate answer.",
"output_regex": "<\\s*([A-Za-z0-9])\\s*>",
"weig... | null | null | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_skywork_no_omni | null | null | {
"row": 24499,
"question_template": "\"{\\\"prefix\\\":\\\"\\\",\\\"suffix\\\":\\\"\\\",\\\"template\\\":\\\"\\\\n{question}\\\\n\\\\nRemember to put your final answer inside \\\\\\\\boxed{}.\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_skywork_no_omni | null | null | {
"row": 80587,
"question_template": "\"{\\\"prefix\\\":\\\"\\\",\\\"suffix\\\":\\\"\\\",\\\"template\\\":\\\"\\\\n{question}\\\\n\\\\nYour final answer should be in \\\\\\\\boxed{}.\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.875 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"6 1\r\npolice\r\np m\r\n",
"11 6\r\nabacabadaba\r\na b\r\nb c\r\na d\r\ne g\r\nf a\r\nb b\r\n",
"1 1\r\nf\r\nz h\r\n",
"1 1\r\na\r\na b\r\n",
"10 10\r\nlellelleel\r\ne l\r\ne l\r\ne l\r\ne l\r\ne l\r\ne e\r\nl l\r\nl e\r\nl l\r\ne e\r\n"
],
"out... | a0f73a01229d6d09ba85fb2e26bbd322 | codeforces | null | null | null |
569 | {
"input": [
{
"role": "system",
"content": "Today's date is Thursday, 2023-11-30 and the current time is 23:59:00. Remember the current date and time when answering queries. Meetings must not start before 9am or end after 6pm."
},
{
"role": "user",
"content": "Make bar charts of s... | [] | workbench_analytics | workbench | {
"type": "responses_api_agents",
"name": "workplace_assistant_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_workbench | null | null | null | null | null | null | null | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "Which of the following options most accurately addresses the question? Choose the best answer and provide only the corresponding option identifier, giving your final answer as: Answer: *X* in italics, with the correct option identifier in place of X, at the e... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "392 Torr"
},
{
"B": "368 Torr"
},
{
"C": "418 Torr"
},
{
"D": "570 Torr"
},
{
"E": "760 Torr"
},
{
"F": "1152 Torr"
},
{
"G": "292 Torr"
},
{
"H": "450 Torr"
},
{
"I": "520 Torr"
},
{
"J": "608 Torr"
}
] | null | D | 39edca59-995b-5099-a380-299704f7b774 | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 0.25
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 1
}
] | {
"template_id": "mcqa_generated_087",
"template_prompt": "Which of the following options most accurately addresses the question? Choose the best answer and provide only the corresponding option identifier, giving your final answer as: Answer: *X* in italics, with the correct option identifier in place of X, at the... | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "Consider the following question carefully and select the correct response. Provide the selected option at the end of your response in this exact format: Selected Option -> X.\n\nAn online forum moderator reviews user-submitted posts and routinely corrects spe... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "No, because the moderator altered the content of the post."
},
{
"B": "No, because the false statements were published under the moderator’s supervision."
},
{
"C": "Yes, because the edits did not contribute to the defamatory nature of the content."
},
{
"D": "No, because the mod... | null | C | 50b67c51-490d-575f-9d74-96e6d5f019cd | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 0.125
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0.875
}
] | {
"template_id": "mcqa_generated_010",
"template_prompt": "Consider the following question carefully and select the correct response. Provide the selected option at the end of your response in this exact format: Selected Option -> X.\n\n{problem}",
"output_regex": "Selected Option\\s*->\\s*([A-Za-z0-9])\\s*",
"... | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "The final answer must be placed in \\boxed{} format at the end of your response.\n\nA blackbody is placed in a medium with a refractive index of 1.5. If the first radiation constant \\( C_1 = 3.742 \\times 10^{-16} \\, \\text{W} \\cdot \\text{m}^2 \\) in vacu... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.625 | 8 | 5 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "\\( 1.663 \\times 10^{-16} \\, \\text{W} \\cdot \\text{m}^2 \\)"
},
{
"B": "\\( 2.495 \\times 10^{-16} \\, \\text{W} \\cdot \\text{m}^2 \\)"
},
{
"C": "\\( 3.742 \\times 10^{-16} \\, \\text{W} \\cdot \\text{m}^2 \\)"
},
{
"D": "\\( 5.613 \\times 10^{-16} \\, \\text{W} \\cdot \\te... | null | A | 4f13cc6e-4eb5-5110-800e-52477137e0e7 | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 0.625
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0.875
}
] | {
"template_id": "mcqa_generated_015",
"template_prompt": "The final answer must be placed in \\boxed{} format at the end of your response.\n\n{problem}\n\nChoose the best answer from the options given and respond with only the corresponding letter.",
"output_regex": "\\\\boxed\\{\\s*([A-Za-z0-9])\\s*\\}",
"wei... | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"content": "Format your response as an object matching the provided JSON schema: {\"type\": \"object\", \"required\": [\"location\", \"photographer\", \"equipment\", \"shootDetails\", \"transportation\", \"permissions\", \"postProcessing\"], \"additionalProperties\": false, \"properties\": {\... | null | null | null | {
"type": "responses_api_agents",
"name": "structured_outputs_simple_agent"
} | 0.375 | 8 | 3 | nano_v3_sft_profiled_structured_outputs | null | null | null | null | null | null | null | null | null | null | null | null | {"type": "object", "required": ["location", "photographer", "equipment", "shootDetails", "transportation", "permissions", "postProcessing"], "additionalProperties": false, "properties": {"location": {"type": "object", "required": ["country", "city", "landmark", "coordinates"], "additionalProperties": false, "properties... | json | 7 |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"10\n2\n5 190511 174892 60413 161099 192095\n2 190511 174892\n2\n2 25224 33915\n2 3156 25224\n2\n2 102801 58269\n2 102801 58269\n2\n2 73575 66574\n2 73575 66574\n2\n2 191259 156476\n2 191259 156476\n2\n2 94903 80911\n2 94903 80911\n2\n2 134838 86551\n2 134838 86551\n2\n2 64258 ... | edb20f8607becf6dfa45f0f913cfafbd | codeforces | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "A baseball player is injured when his wooden bat shatters during a swing. The bat met standard manufacturing practices, and similar bats break occasionally in games. The player sues the manufacturer for negligence, claiming the bat was unreasonably dangerous.... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "For the plaintiff, because any product that breaks during use is defective."
},
{
"B": "For the plaintiff, because the manufacturer failed to warn about breakage risks."
},
{
"C": "For the defendant, because the risk of bat breakage is common knowledge."
},
{
"D": "For the defend... | null | C | 2c9b8fb8-2207-5243-b53b-7994804dc35d | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 0.625
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0.25
}
] | {
"template_id": "mcqa_generated_104",
"template_prompt": "{problem}\n\nWhich option best answers the question? Choose the corresponding option identifier, and end your response with the correct choice in this format: <<X>>.",
"output_regex": "<<\\s*([A-Za-z0-9])\\s*>>",
"weight": 0.005952381,
"prompt_type": ... | null | null | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_dapo17k | null | null | {
"row": 1790155,
"question_template": "\"{\\\"prefix\\\":\\\"Solve this problem. Enclose your final answer in \\\\\\\\boxed{}.\\\",\\\"suffix\\\":\\\"\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
32,586 | {
"input": [
{
"role": "user",
"content": "When answering, please adhere to these constraints: In your response, the word bar should appear 3 times, Your entire response should be in English, and in all capital letters, and The first word of your response should be the word perception. what can cause ... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_instruction_following | [
{
"keyword": "bar",
"frequency": 3,
"relation": "at least"
},
null,
{
"first_word": "perception"
}
] | null | null | null | null | null | null | [
"keywords:word_count_different_numbers",
"change_case:english_capital",
"first_word:first_word_answer"
] | When answering, please adhere to these constraints: In your response, the word bar should appear 3 times, Your entire response should be in English, and in all capital letters, and The first word of your response should be the word perception. what can cause lower back pain | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_skywork_no_omni | null | null | {
"row": 104695,
"question_template": "\"{\\\"prefix\\\":\\\"\\\",\\\"suffix\\\":\\\"\\\",\\\"template\\\":\\\"Your task is to find the solution to this math problem. Make sure your answer is inside \\\\\\\\boxed{}.\\\\n{question}\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.75 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"5\r\n2 6 5 6 2\r\n9\r\n1 5 10\r\n2 5\r\n1 1 3\r\n3 3 6\r\n3 8 9\r\n1 2 9\r\n2 3\r\n2 2\r\n2 4\r\n"
],
"outputs": [
"10\r\n7\r\n9\r\n7\r\n"
]
}
} | c34bdd6b163d29b1f7c5157908054810 | codeforces | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"5\r\n0 1 2 1 2\r\n",
"4\r\n0 1 2 3\r\n",
"1\r\n0\r\n",
"8\r\n3 1 4 0 4 2 4 5\r\n",
"100\r\n81 96 65 28 4 40 5 49 5 89 48 70 94 70 17 58 58 1 61 19 45 33 46 19 22 83 56 67 62 82 57 16 29 36 84 71 42 66 78 54 73 45 82 80 67 88 79 69 61 66 5 36 24 60 96 21... | 3b6a7a1f26cad9204a95f043507a099e | codeforces | null | null | null |
8,440 | {
"input": [
{
"role": "user",
"content": "When answering, please adhere to these constraints:\n- Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.')\n\nجهت استخدام یک برنامه نویس گه مسایلی بررسی شود و چه سوالتی پرسیده شود؟"
}
],
"tools": ... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_instruction_following | [
null
] | null | null | null | null | null | null | [
"detectable_format:constrained_response"
] | When answering, please adhere to these constraints:
- Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.')
جهت استخدام یک برنامه نویس گه مسایلی بررسی شود و چه سوالتی پرسیده شود؟ | null | null | null | null | null | null |
null | null | null | null | null | {
"type": "responses_api_agents",
"name": "math_with_judge_simple_agent"
} | 0.875 | 8 | 7 | nano_v3_sft_profiled_dapo17k | null | null | {
"row": 1787139,
"question_template": "\"{\\\"prefix\\\":\\\"\\\",\\\"suffix\\\":\\\"Please enclose your answer in \\\\\\\\boxed{}.\\\"}\""
} | null | null | null | null | null | null | null | null | null | null | null | null |
33,369 | {
"input": [
{
"role": "user",
"content": "more headline options like hear her story. Please incorporate these requirements: Your entire response should be in English, and in all lowercase letters. No capital letters are allowed and The first word of each sentence should be the word pain"
}
],
... | null | null | null | {
"type": "responses_api_agents",
"name": "instruction_following_simple_agent"
} | 0.75 | 8 | 6 | nano_v3_sft_profiled_instruction_following | [
null,
{
"first_word": "pain"
}
] | null | null | null | null | null | null | [
"change_case:english_lowercase",
"first_word:first_word_sent"
] | more headline options like hear her story. Please incorporate these requirements: Your entire response should be in English, and in all lowercase letters. No capital letters are allowed and The first word of each sentence should be the word pain | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "Conclude your response with the phrase \"Correct Option: X\", where X is the option identifier corresponding to the correct choice (e.g., A, B, C, D, 1, 2, 3). Choose the most appropriate option from the given choices.\n\nA federal statute mandates that state... | null | null | null | {
"type": "responses_api_agents",
"name": "mcqa_simple_agent"
} | 0.125 | 8 | 1 | nano_v3_sft_profiled_stem_mcqa | null | [
{
"A": "The Tenth Amendment allows Congress to impose procedural rules on state courts when necessary."
},
{
"B": "The Supremacy Clause invalidates any state law conflicting with federal law."
},
{
"C": "Congress may regulate state court procedures when essential to the vindication of federal ri... | null | C | 3c94c788-d679-5576-b2af-71e71839d079 | [
{
"model_hf_path": "Qwen/Qwen3-235B-A22B-Instruct-2507",
"num_generations": 8,
"pass_rate": 0.25
},
{
"model_hf_path": "openai/gpt-oss-120b",
"num_generations": 8,
"pass_rate": 0.875
}
] | {
"template_id": "mcqa_generated_020",
"template_prompt": "Conclude your response with the phrase \"Correct Option: X\", where X is the option identifier corresponding to the correct choice (e.g., A, B, C, D, 1, 2, 3). Choose the most appropriate option from the given choices.\n\n{problem}",
"output_regex": "Corr... | null | null | null | null | null | null | null | null |
null | {
"input": [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n``... | null | null | null | {
"type": "responses_api_agents",
"name": "code_gen_simple_agent"
} | 0.375 | null | null | nano_v3_sft_profiled_comp_coding_50tests | null | null | null | null | null | null | null | null | null | {
"unit_tests": {
"inputs": [
"2\r\n3\r\n3 1 2\r\n6\r\n4 1 5 4 1 1\r\n"
],
"outputs": [
"2 1 0\r\n3 2 4 4 4 4\r\n"
]
}
} | c504e4019d7a88be443885047040a61d | codeforces | null | null | null |
End of preview. Expand in Data Studio
Dataset Description:
Nemotron-3-Nano-RL-Training-Blend is a curated dataset blend used to train the Nemotron-3-Nano-30B-A3B model. The blend consists of the following component datasets, with mixing ratios shown in parentheses:
- nvidia/Nemotron-RL-instruction_following (0.17)
- nvidia/Nemotron-RL-knowledge-mcqa (0.20)
- nvidia/Nemotron-RL-agent-workplace_assistant (0.10)
- nvidia/Nemotron-RL-instruction_following-structured_outputs (0.05)
- nvidia/Nemotron-RL-coding-competitive_coding (0.25)
- BytedTsinghua-SIA/DAPO-Math-17k (0.10)
- Skywork/Skywork-OR1-RL-Data (excluding OmniMath) (0.12)
For the BytedTsinghua-SIA/DAPO-Math-17k and Skywork/Skywork-OR1-RL-Data data in this blend, instead of replicating the data in this dataset, placeholders are used that point to entries in the original datasets. A script is provided that can be used to download the data from the original datasets into the blend. For each dataset an user elects to use, the user is responsible for checking if the dataset license is fit for the intended purpose.
For the nvidia/Nemotron-RL-coding-competitive_coding data, we do not include samples from the tacos or apps subsets.
The dataset is preprocessed according to the curriculum described in the Nemotron-3-Nano-30B-A3B technical report (http://research.nvidia.com/labs/nemotron). Samples are ordered from higher pass-rate (easier) to lower pass-rate (harder), ensuring a balanced learning progression.
This dataset is released as part of NVIDIA NeMo Gym, a framework for building reinforcement learning environments to train large language models. NeMo Gym contains a growing collection of training environments and datasets to enable Reinforcement Learning from Verifiable Reward (RLVR).
NeMo Gym is an open-source library within the NVIDIA NeMo framework, NVIDIA's GPU accelerated, end-to-end training framework for large language models (LLMs), multi-modal models and speech models.
This dataset is part of the NeMo Gym family.
This dataset is ready for commercial use.
Dataset Owner(s):
NVIDIA Corporation
Dataset Creation Date:
12/20/2025
License/Terms of Use:
ODC Attribution License
Intended Usage:
To be used with NeMo Gym for post-training LLMs.
Dataset Characterization
** Data Collection Method
- [Synthetic]
** Labeling Method
[Synthetic]
This dataset contains synthetic data created using
- nvidia/Nemotron-RL-instruction_following (0.17)
- nvidia/Nemotron-RL-knowledge-mcqa (0.20)
- nvidia/Nemotron-RL-agent-workplace_assistant (0.10)
- nvidia/Nemotron-RL-instruction_following-structured_outputs (0.05)
- nvidia/Nemotron-RL-coding-competitive_coding (0.25)
- BytedTsinghua-SIA/DAPO-Math-17k (0.10)
- Skywork/Skywork-OR1-RL-Data (excluding OmniMath) (0.12)
Dataset Format
Text Only, Compatible with NeMo Gym
Dataset Quantification
Number of records: 93244 samples
Total Data Storage: 6.92 GB
Reference(s):
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
- Downloads last month
- 124