Jclennon/TableMind
8B
•
Updated
•
2
Datasets:
Modalities:
Text
Size:
10K - 100K
Dataset Viewer
data_source
stringclasses 3
values | prompt
listlengths 2
2
| ability
stringclasses 1
value | reward_model
dict | extra_info
dict |
|---|---|---|---|---|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4914.csv` in your code execution environment.\n\nTable Title: Watford F.C.\nTable Content:\n| Name | Year inducted | Position | Apps | Goals |\n| --- | --- | --- | --- | --- |\n| Luther Blissett | 2003 | Forward | 503 | 186 |\n| Tony Coton | 2004 | Goalkeeper | 291 | 0 |\n| John McClelland | 2005 | Defender | 234 | 3 |\n| Tommy Mooney | 2006 | Forward | 287 | 64 |\n| Les Taylor | 2007 | Midfielder | 211 | 20 |\n| David James | 2008 | Goalkeeper | 98 | 0 |\n| Ian Bolton | 2009 | Defender | 287 | 36 |\n| Nigel Gibbs | 2010 | Defender | 491 | 7 |\n| Duncan Welbourne | 2011 | Defender | 457 | 25 |\n| Ross Jenkins | 2012 | Forward | 398 | 142 |\n| Robert Page | 2013 | Defender | 218 | 2 |\n\n\nQuestion\nwhat is the total number of apps and goals for luther blissett?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"689"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4914",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4200.csv` in your code execution environment.\n\nTable Title: Crazy Town\nTable Content:\n| Title | Year | Peak chart positions\\nUS | Peak chart positions\\nUS\\nAlt. | Peak chart positions\\nUS\\nMain. Rock | Peak chart positions\\nAUS | Peak chart positions\\nAUT | Peak chart positions\\nFIN | Peak chart positions\\nGER | Peak chart positions\\nNLD | Peak chart positions\\nSWI | Peak chart positions\\nUK | Album |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| \"Toxic\" | 1999 | — | — | — | — | — | — | — | — | — | — | The Gift of Game |\n| \"Darkside\" | 2000 | — | — | — | — | — | — | — | — | — | — | The Gift of Game |\n| \"Butterfly\" | 2000 | 1 | 1 | 21 | 4 | 1 | 2 | 1 | 8 | 1 | 3 | The Gift of Game |\n| \"Revolving Door\" | 2001 | — | — | — | 76 | 29 | 19 | 26 | 71 | 43 | 23 | The Gift of Game |\n| \"Drowning\" | 2002 | — | 24 | 24 | — | 45 | — | 45 | — | — | 50 | Darkhorse |\n| \"Hurt You So Bad\" | 2003 | — | — | — | — | — | — | — | — | — | — | Darkhorse |\n\n\nQuestion\nby how many chart positions higher did \"revolving door\" peak in the uk compared to the peak position of \"drowning\" in the uk?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"27"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4200",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-7094.csv` in your code execution environment.\n\nTable Title: Andy Roddick\nTable Content:\n| Outcome | Year | Championship | Surface | Opponent | Score |\n| --- | --- | --- | --- | --- | --- |\n| Runner-up | 2002 | Canada (Toronto) (1) | Hard | Guillermo Cañas | 4–6, 5–7 |\n| Winner | 2003 | Montreal | Hard | David Nalbandian | 6–1, 6–3 |\n| Winner | 2003 | Cincinnati | Hard | Mardy Fish | 4–6, 7–6(7–3), 7–6(7–4) |\n| Winner | 2004 | Miami | Hard | Guillermo Coria | 6–7(2–7), 6–3, 6–1, ret. |\n| Runner-up | 2004 | Toronto (2) | Hard | Roger Federer | 5–7, 3–6 |\n| Runner-up | 2005 | Cincinnati | Hard | Roger Federer | 3–6, 5–7 |\n| Winner | 2006 | Cincinnati (2) | Hard | Juan Carlos Ferrero | 6–3, 6–4 |\n| Runner-up | 2010 | Indian Wells | Hard | Ivan Ljubičić | 6–7(3–7), 6–7(5–7) |\n| Winner | 2010 | Miami (2) | Hard | Tomáš Berdych | 7–5, 6–4 |\n\n\nQuestion\nhow many times was the championship in miami?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"2"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-7094",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-77.csv` in your code execution environment.\n\nTable Title: MXR Yorkshire\nTable Content:\n| Service | Service ID | Bit rate | Audio channels | Description | Analogue availability |\n| --- | --- | --- | --- | --- | --- |\n| Capital Yorkshire | C3AA | 128 kbit/s | Joint stereo | Dance and R'n'B | 105.1 MHz (South & West Yorkshire)\\n105.6 MHz (Bradford & Sheffield)\\n105.8 MHz (Humberside) |\n| Choice FM | C0CE | 128 kbit/s | Joint stereo | R'n'B and Hip-hop | — |\n| Heart London | CCCD | 128 kbit/s | Joint stereo | Adult contemporary | — |\n| Gold | C2CE | 64 kbit/s | Mono LSF | Oldies, 60s, 70s, 80s | — |\n| Real Radio (Yorkshire) | C3A4 | 128 kbit/s | Joint stereo | Contemporary | 106.2 MHz (South & West Yorkshire)\\n107.6 MHz (Bradford & Halifax)\\n107.7 MHz (Sheffield) |\n| Real Radio XS | C8C5 | 128 kbit/s | Joint stereo | Classic rock | — |\n| UCB Gospel | CED0 | 64 kbit/s | Mono LSF | Christian | — |\n| UCB Inspirational | CFD0 | 64 kbit/s | Mono LSF | Christian | — |\n| XFM | C0B8 | 128 kbit/s | Joint stereo | Indie / alternative / rock music | — |\n| Yorkshire Radio | CFCD | 128 kbit/s | Joint stereo | Pop music and sport | — |\n| DAB Guide | E1C000A9 | 8 kbit/s | Data | Hidden service, EPG data | — |\n\n\nQuestion\nwhat is the number of christian radio stations broadcasted by mxr yorkshire?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"2"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-77",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-12591.csv` in your code execution environment.\n\nTable Title: Luís Jesus\nTable Content:\n| Year | Competition | Venue | Position | Event | Notes |\n| --- | --- | --- | --- | --- | --- |\n| 1998 | Turin Marathon | Turin, Italy | 3rd | Marathon | 2:12:59 |\n| 2003 | Lisbon Marathon | Lisbon, Portugal | 1st | Marathon | 2:15:31 |\n| 2004 | Vienna Marathon | Vienna, Austria | 3rd | Marathon | 2:11:24 |\n| 2004 | Berlin Marathon | Berlin, Germany | 5th | Marathon | 2:09:08 |\n| 2005 | World Championships | Helsinki, Finland | 18th | Marathon | 2:16:33 |\n| 2006 | Paris Marathon | Paris, France | 4th | Marathon | 2:08:55 |\n| 2006 | Lisbon Marathon | Lisbon, Portugal | 1st | Marathon | 2:21:08 |\n| 2007 | World Championships | Osaka, Japan | — | Marathon | DNS |\n\n\nQuestion\nhow long did luis jesus take to finish in turin,italy in 1998?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"2:12:59"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-12591",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-9444.csv` in your code execution environment.\n\nTable Title: 2012–13 UCI America Tour\nTable Content:\n| Date | Race Name | Location | UCI Rating | Winner | Team |\n| --- | --- | --- | --- | --- | --- |\n| 6 January | Copa América de Ciclismo | Brazil | 1.2 | Francisco Chamorro (ARG) | Funvic Brasilinvest-São José dos Campos |\n| 11–20 January | Vuelta al Táchira | Venezuela | 2.2 | Yeison Delgado (VEN) | Kino Táchira-Drodínica |\n| 21–27 January | Tour de San Luis | Argentina | 2.1 | Daniel Díaz (ARG) | San Luis Somos Todos |\n| 21–28 April | Vuelta a Guatemala | Guatemala | 2.2 | Óscar Sánchez (COL) | GW Shimano |\n| 1–5 May | Tour of the Gila | United States | 2.2 | Philip Deignan (IRL) | UnitedHealthcare |\n| 2 May | Pan American Cycling Championships – Time Trial | Mexico | CC | Carlos Oyarzun (CHI) | Chile national team |\n| 5 May | Pan American Cycling Championships – Road Race | Mexico | CC | Jonathan Paredes (COL) | Colombia national team |\n| 12–19 May | Tour of California | United States | 2.HC | Tejay Van Garderen (USA) | BMC Racing Team |\n| 2 June | The Philly Cycling Classic | United States | 1.2 | Kiel Reijnen (USA) | UnitedHealthcare |\n| 7–9 June | Coupe des Nations Ville Saguenay | Canada | 2.Ncup | Sondre Enger (NOR) | Norway national team |\n| 9–23 June | Vuelta a Colombia | Colombia | 2.2 | Óscar Sevilla (ESP) | EPM-UNE |\n| 11–16 June | Tour de Beauce | Canada | 2.2 | Nathan Brown (USA) | Bontrager Cycling Team |\n| 7 July | Tour de Delta | Canada | 1.2 | Steve Fisher (USA) | Hagens Berman Cycling |\n| 19–28 July | Vuelta a Venezuela | Venezuela | 2.2 | Carlos José Ochoa (VEN) | Androni Giocattoli-Venezuela |\n| 2–4 August | Tour of Elk Grove | United States | 2.1 | Elia Viviani (ITA) | Cannondale |\n| 6–11 August | Tour of Utah | United States | 2.1 | Tom Danielson (USA) | Garmin-Sharp |\n| 6–11 August | Ruta del Centro | Mexico | 2.2 | Víctor García (ESP) | Depredadores PBG Design |\n| 14–18 August | Vuelta al Sur de Bolivia | Bolivia | 2.2 | Óscar Soliz (BOL) | Pio Rico |\n| 19–25 August | USA Pro Cycling Challenge | United States | 2.HC | Tejay Van Garderen (USA) | BMC Racing Team |\n| 28 Aug–1 Sep | Tour do Rio | Brazil | 2.2 | Óscar Sevilla (ESP) | EPM-UNE |\n| 3–8 September | Tour of Alberta | Canada | 2.1 | Rohan Dennis (AUS) | Garmin-Sharp |\n| 7 September | Bucks County Classic | United States | 1.2 | Kiel Reijnen (USA) | UnitedHealthcare |\n\n\nQuestion\nwhat is the winner name and team for the copa américa de ciclismo race?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Francisco Chamorro (ARG)",
"Funvic Brasilinvest-São José dos Campos"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-9444",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-12634.csv` in your code execution environment.\n\nTable Title: Mexican Grand Prix\nTable Content:\n| Year | Driver | Constructor | Location | Report |\n| --- | --- | --- | --- | --- |\n| 1992 | Nigel Mansell | Williams-Renault | Hermanos Rodriguez | Report |\n| 1991 | Riccardo Patrese | Williams-Renault | Hermanos Rodriguez | Report |\n| 1990 | Alain Prost | Ferrari | Hermanos Rodriguez | Report |\n| 1989 | Ayrton Senna | McLaren-Honda | Hermanos Rodriguez | Report |\n| 1988 | Alain Prost | McLaren-Honda | Hermanos Rodriguez | Report |\n| 1987 | Nigel Mansell | Williams-Honda | Hermanos Rodriguez | Report |\n| 1986 | Gerhard Berger | Benetton-BMW | Hermanos Rodriguez | Report |\n| 1985\\n-\\n1971 | Not held | Not held | Not held | Not held |\n| 1970 | Jacky Ickx | Ferrari | Magdalena Mixhuca | Report |\n| 1969 | Denny Hulme | McLaren-Ford | Magdalena Mixhuca | Report |\n| 1968 | Graham Hill | Lotus-Ford | Magdalena Mixhuca | Report |\n| 1967 | Jim Clark | Lotus-Ford | Magdalena Mixhuca | Report |\n| 1966 | John Surtees | Cooper-Maserati | Magdalena Mixhuca | Report |\n| 1965 | Richie Ginther | Honda | Magdalena Mixhuca | Report |\n| 1964 | Dan Gurney | Brabham-Climax | Magdalena Mixhuca | Report |\n| 1963 | Jim Clark | Lotus-Climax | Magdalena Mixhuca | Report |\n| 1962 | Trevor Taylor\\n Jim Clark | Lotus-Climax | Magdalena Mixhuca | Report |\n\n\nQuestion\nwho won the year before alain prost?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Riccardo Patrese"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-12634",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-160.csv` in your code execution environment.\n\nTable Title: France at the 1932 Summer Olympics\nTable Content:\n| Medal | Name | Sport | Event | Date |\n| --- | --- | --- | --- | --- |\n| Gold | Louis Chaillot, Maurice Perrin | Cycling | Men's tandem | August 3 |\n| Gold | Xavier Lesage | Equestrian | Individual dressage | August 10 |\n| Gold | André Jousseaume, Xavier Lesage,\\nCharles Marion | Equestrian | Team dressage | August 10 |\n| Gold | Georges Buchard, Philippe Cattiau,\\nFernand Jourdant, Jean Piot,\\nBernard Schmetz, Georges Tainturier | Fencing | Men's team épée | August 7 |\n| Gold | René Bondoux, René Bougnol,\\nPhilippe Cattiau, Edward Gardère,\\nRené Lemoine, Jean Piot | Fencing | Men's team foil | August 1 |\n| Gold | Jacques Lebrun | Sailing | Snowbird class | August 12 |\n| Gold | Raymond Suvigny | Weightlifting | Men's 60 kg | July 31 |\n| Gold | René Duverger | Weightlifting | Men's 67.5 kg | July 30 |\n| Gold | Louis Hostin | Weightlifting | Men's 82.5 kg | July 30 |\n| Gold | Charles Pacôme | Wrestling | Men's freestyle lightweight | August 3 |\n| Silver | Louis Chaillot | Cycling | Men's sprint | August 3 |\n| Silver | Paul Chocque, Amédée Fournier,\\nRené Le Grèves, Henri Mouillefarine | Cycling | Men's team pursuit | August 2 |\n| Silver | Charles Marion | Equestrian | Individual dressage | August 10 |\n| Silver | Georges Buchard | Fencing | Men's épée | August 9 |\n| Silver | Jean Taris | Swimming | Men's 400 m freestyle | August 10 |\n| Bronze | Paul Winter | Athletics | Men's discus throw | August 3 |\n| Bronze | Charles Rampelberg | Cycling | Men's 1000 m time trial | August 1 |\n| Bronze | Pierre Brunet, Anselme Brusa,\\nAndré Giriat | Rowing | Men's coxed pair | August 13 |\n| Bronze | Louis François | Wrestling | Men's Greco-Roman bantamweight | August 7 |\n\n\nQuestion\nhow many gold medals did this country win during these olympics?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"10"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-160",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-13551.csv` in your code execution environment.\n\nTable Title: Slipping Away (Moby song)\nTable Content:\n| Version | Length | Album | Remixed by | Year | Comment |\n| --- | --- | --- | --- | --- | --- |\n| Single Version / Radio Edit | 3:39 | Go – The Very Best of Moby | MHC aka Philip Larsen and Chis Smith | 2006 | Remixed version with dance sonorities, with English and French lyrics which alternate. This version is more rhythmic than the original one. |\n| Extended Remix | 6:48 | — | MHC aka Philip Larsen and Chis Smith | 2006 | Similar to the previous but longer. |\n| Axwell Remix | 7:24 | — | Axwell | 2006 | Used in a scene in the 2008 movie 21. |\n| Enzo Mori & Stephan Clark Remix | 7:10 | — | Enzo Mori and Stephan Clark | 2006 | |\n| MHC club Remix | 7:31 | — | MHC aka Philip Larsen and Chis Smith | 2006 | |\n| Zloot Remix | 4:36 | — | Toni Toolz | 2006 | |\n| Music Video | 3:58 | — | — | 2006 | |\n\n\nQuestion\nwhat is the total amount of remix versions?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"5"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-13551",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-5722.csv` in your code execution environment.\n\nTable Title: Biathlon at the Winter Paralympics\nTable Content:\n| Rank | Nation | Gold | Silver | Bronze | Total |\n| --- | --- | --- | --- | --- | --- |\n| 1 | Germany | 17 | 9 | 14 | 40 |\n| 2 | Russia | 12 | 16 | 8 | 36 |\n| 3 | Ukraine | 6 | 11 | 9 | 26 |\n| 4 | Norway | 6 | 2 | 7 | 15 |\n| 5 | France | 5 | 4 | 3 | 12 |\n| 6 | Switzerland | 3 | 5 | 3 | 11 |\n| 7 | Finland | 3 | 2 | 4 | 9 |\n| 8 | Japan | 2 | 2 | 1 | 5 |\n| 9 | Netherlands | 2 | 0 | 1 | 3 |\n| 10 | Sweden | 1 | 2 | 2 | 5 |\n| 11 | Denmark | 1 | 0 | 1 | 2 |\n| 12 | Unified Team | 1 | 0 | 0 | 1 |\n| 13 | Austria | 0 | 4 | 0 | 4 |\n| 14 | Slovakia | 0 | 2 | 1 | 3 |\n| 15 | Italy | 0 | 0 | 1 | 1 |\n| 15 | Poland | 0 | 0 | 1 | 1 |\n| 15 | Canada | 0 | 0 | 1 | 1 |\n| 15 | Belarus | 0 | 0 | 1 | 1 |\n| 15 | United States | 0 | 0 | 1 | 1 |\n| Total 19 nations | Total 19 nations | 59 | 59 | 59 | 177 |\n\n\nQuestion\nonly one team has won more than 10 bronze medals in the biathlon at the winter paralympics. which team is it?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Germany"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-5722",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4481.csv` in your code execution environment.\n\nTable Title: List of lakes of Turkey\nTable Content:\n| Name in English | Name in Turkish | Area (km2) | Depth | Location (districts and/or provinces) |\n| --- | --- | --- | --- | --- |\n| Lake Van | Van Gölü | 3755 km2 | 451 m | Van, Bitlis |\n| Lake Tuz | Tuz Gölü | 1500 km2 | 2 m | Aksaray, Ankara, Konya |\n| Lake Beyşehir | Beyşehir Gölü | 656 km2 | 10 m | Beyşehir in Konya, Isparta |\n| Lake Eğirdir | Eğirdir Gölü | 482 km2 | | Isparta |\n| Lake İznik | İznik Gölü | 308 km2 | | İznik in Bursa, Yalova |\n| Lake Burdur | Burdur Gölü | 200 km2 | | Burdur, Isparta |\n| Lake Manyas | Manyas Gölü | 166 km2 | | Balıkesir |\n| Lake Acıgöl | Acıgöl | 153 km2 | | Denizli, Afyonkarahisar |\n| Lake Uluabat | Uluabat Gölü | 134 km2 | 1–2 m | Bursa |\n| Lake Çıldır | Çıldır Gölü | 115 km2 | | Ardahan, Kars |\n| Lake Palas Tuzla | Palas Tuzla Gölü | 106 km2 | 15 m | Palas/Kayseri |\n| Lake Akşehir | Akşehir Gölü | 105 km2 | | Akşehir in Konya, Afyonkarahisar |\n| Lake Eber | Eber Gölü | 104 km2 | | Afyonkarahisar |\n| Lake Erçek | Erçek Gölü | 98 km2 | | Van |\n| Lake Hazar | Hazar Gölü | 86 km2 | | Elazığ |\n| Lake Bafa | Bafa Gölü | 60 km2 | | Aydın, Muğla |\n| Lake Köyceğiz | Köyceğiz Gölü | 52 km2 | | Köyceğiz in Muğla |\n| Lake Işıklı | Işıklı Gölü | 49 km2 | | Denizli |\n| Lake Nazik | Nazik Gölü | 48 km2 | | Bitlis |\n| Lake Sapanca | Sapanca Gölü | 47 km2 | | Sakarya Province |\n| Lake Salda | Salda Gölü | 45 km2 | 184 m | Burdur |\n| Lake Yay | Yay Gölü | 37 km2 | | Kayseri |\n| Lake Akyatan | Akyatan Gölü | 35 km2 | | Adana |\n| Lake Balık | Balık Gölü | 34 km2 | | Doğubeyazıt in Ağrı |\n| Lake Marmara | Marmara Gölü | 34 km2 | | Salihli, Gölmarmara in Manisa |\n| Lake Çöl | Çöl Gölü | 32 km2 | | Ankara |\n| Lake Durusu (Lake Terkos) | Durusu Gölü | 25 km2 | | İstanbul |\n| Lake Karine | Karine Gölü | 24 km2 | | |\n| Lake Tuzla | Tuzla Gölü | 23 km2 | | Tuzla |\n| Lake Küçükçekmece | Küçükçekmece Gölü | 16 km2 | | Küçükçekmece, İstanbul |\n| Lake Yaraşlı | Yaraşlı Gölü | 16 km2 | | Burdur |\n| Lake Haçlı | Haçlı Gölü | 16 km2 | | Muş |\n| Lake Seyfe | Seyfe Gölü | 15 km2 | | Kırşehir |\n| Lake Akyayan | Akyayan Gölü | 15 km2 | | |\n| Lake Hozapin | Hozapin Gölü | 14 km2 | | |\n| Lake Arin | Arin Gölü | 13 km2 | | |\n| Lake Nemrut | Nemrut Gölü | 12 km2 | | Bitlis Province |\n| Lake Balık | Balık Gölü | 12 km2 | | |\n| Lake Büyükçekmece | Büyükçekmece Gölü | 11 km2 | | Büyükçekmece, Istanbul |\n| Lake Boluk | Boluk Gölü | 11 km2 | | |\n| Lake Akdoğan | Akdoğan Gölü | 11 km2 | | |\n| Lake Çavuşlu | Çavuşlu Gölü | 9 km2 | | |\n| Lake Düden | Düden Gölü | 8 km2 | | |\n| Lake Gala | Gala Gölü | 8 km2 | | Edirne |\n| Lake Karataş | Karataş Gölü | 6 km2 | | |\n| Lake Mogan | Mogan Gölü | 6 km2 | | Ankara |\n| Paradeniz | Paradeniz | 4 km2 | | Mersin |\n| Lake Eymir | Eymir Gölü | 1.8 km2 | | Ankara |\n| Lake Abant | Abant Gölü | 1.28 km2 | 18 m | Bolu |\n| Lake Gölcük | Gölcük Gölü | 1 km2 | | İzmir |\n\n\nQuestion\nwhich lake has the most area and it locations\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Lake Van",
"Van, Bitlis"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4481",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-13885.csv` in your code execution environment.\n\nTable Title: Zbigniew Rybczyński\nTable Content:\n| Year | Film Title | Duration | Film Type | Shoot Location |\n| --- | --- | --- | --- | --- |\n| 1972 | Kwadrat (Square) | 4:40 | 35 mm short film | PWSFTviT Łódź, Poland |\n| 1972 | Take Five | 3:36 | 35 mm short film | PWSFTviT Łódź, Poland |\n| 1973 | Plamuz (Music Art) | 9:38 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1974 | Zupa (Soup) | 8:22 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1975 | Nowa Książka (New Book) | 10:26 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1975 | Lokomotywa (Locomotive) | 9:38 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1975 | Święto (Holiday) | 9:38 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1976 | Oj! Nie Mogę Się Zatrzymać! (Oh, I Can't Stop!) | 10:07 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1976 | Weg Zum Nachbarn (Way To Your Neighbor) | 2:30 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1977 | Piątek - Sobota (Friday - Saturday) | 3:00 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1979 | Mein Fenster (My Window) | 2:26 | 35 mm short film | Vienna |\n| 1980 | Tango | 8:14 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1980 | Media | 1:36 | 35 mm short film | SMFF Se-Ma-For Łódź, Poland |\n| 1980 | Sceny Narciarskie z Franzem Klammeren (Ski Scenes with Franz Klammer) | 9:38 | 35 mm documentary film | in collaboration with B. Dziworski, WFO Łódź, Poland and Signal Film, Vienna |\n| 1981 | Wdech-Wydech (Inhale-Exhale) | 2:26 | 35 mm short film | in collaboration with B. Dziworski, SMFF Se-Ma-For Łódź, for TVP, Poland |\n\n\nQuestion\nhow many films had a duration below 5 minutes?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"7"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-13885",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-415.csv` in your code execution environment.\n\nTable Title: United States presidential election in New York, 2004\nTable Content:\n| County | Kerry | Votes | Bush | Votes | Others | Votes |\n| --- | --- | --- | --- | --- | --- | --- |\n| Bronx | 82.8% | 283,994 | 16.5% | 56,701 | 0.7% | 2,284 |\n| Manhattan | 82.1% | 526,765 | 16.7% | 107,405 | 1.2% | 7,781 |\n| Brooklyn | 74.9% | 514,973 | 24.3% | 167,149 | 0.8% | 5,762 |\n| Queens | 71.7% | 433,835 | 27.4% | 165,954 | 0.9% | 5,603 |\n| Tompkins | 64.2% | 27,229 | 33.0% | 13,994 | 2.8% | 1,179 |\n| Albany | 60.7% | 89,323 | 37.3% | 54,872 | 2.0% | 3,004 |\n| Westchester | 58.1% | 229,849 | 40.3% | 159,628 | 1.6% | 6,293 |\n| Erie | 56.4% | 251,090 | 41.4% | 184,423 | 2.2% | 9,625 |\n| Saint Lawrence | 54.7% | 22,857 | 43.2% | 18,029 | 2.1% | 869 |\n| Ulster | 54.3% | 47,602 | 43.1% | 37,821 | 2.6% | 2,289 |\n| Onondaga | 54.2% | 116,381 | 43.8% | 94,006 | 2.0% | 4,202 |\n| Nassau | 52.2% | 323,070 | 46.6% | 288,355 | 1.1% | 6,918 |\n| Clinton | 52.2% | 17, 624 | 45.4% | 15,330 | 2.3% | 782 |\n| Franklin | 52.1% | 9,543 | 45.8% | 8,383 | 2.1% | 390 |\n| Schenectady | 51.8% | 35,971 | 46.2% | 32,066 | 2.1% | 1,432 |\n| Columbia | 51.2% | 15,929 | 46.5% | 14,457 | 2.3% | 717 |\n| Monroe | 50.6% | 173,497 | 47.7% | 163,545 | 1.7% | 5,939 |\n| Broome | 50.4% | 46,281 | 47.4% | 43,568 | 2.2% | 2,041 |\n| Rensselaer | 49.7% | 36,075 | 47.9% | 34,734 | 2.4% | 1,705 |\n| Suffolk | 49.5% | 315,909 | 48.5% | 309,949 | 2.0% | 12,854 |\n| Niagara | 49.3% | 47,602 | 48.8% | 47,111 | 1.9% | 1,867 |\n| Rockland | 48.9% | 64,191 | 49.6% | 65,130 | 1.5% | 1,910 |\n| Cayuga | 48.6% | 17,534 | 49.2% | 17,743 | 2.1% | 775 |\n| Sullivan | 48.6% | 15,034 | 49.5% | 15,319 | 2.0% | 613 |\n| Otsego | 47.7% | 12,723 | 50.1% | 13,342 | 2.2% | 587 |\n| Dutchess | 47.0% | 58,232 | 51.2% | 63,372 | 1.8% | 2,277 |\n| Cortland | 46.9% | 10,670 | 51.0% | 11,613 | 2.1% | 477 |\n| Oswego | 46.8% | 24,133 | 51.0% | 26,325 | 2.2% | 1,149 |\n| Essex | 45.9% | 8,768 | 51.7% | 9,869 | 2.3% | 445 |\n| Saratoga | 45.6% | 48,730 | 52.5% | 56,158 | 1.9% | 1,985 |\n| Seneca | 45.5% | 6,979 | 52.1% | 7,981 | 2.4% | 365 |\n| Chautauqua | 44.7% | 27,257 | 53.2% | 32,434 | 2.1% | 1,251 |\n| Montgomery | 44.5% | 9,449 | 53.4% | 11,338 | 2.0% | 434 |\n| Orange | 43.8% | 63,394 | 54.7% | 79,089 | 1.5% | 2,190 |\n| Chemung | 43.7% | 17,080 | 54.6% | 21,321 | 1.7% | 674 |\n| Chenango | 43.5% | 9,277 | 54.3% | 11,582 | 2.3% | 482 |\n| Jefferson | 43.5% | 16,860 | 54.7% | 21,231 | 1.8% | 709 |\n| Madison | 43.3% | 13,121 | 54.6% | 16,537 | 2.1% | 629 |\n| Warren | 43.2%' | 13,405 | 54.6% | 16,969 | 2.2% | 685 |\n| Oneida | 42.8% | 40,792 | 54.9% | 52,392 | 2.3% | 2,185 |\n| Richmond (Staten Island) | 42.7% | 68,448 | 56.4% | 90,325 | 0.9% | 1,370 |\n| Washington | 42.3% | 10,624 | 55.1% | 13,827 | 2.6% | 652 |\n| Ontario | 42.2% | 21,166 | 55.9% | 27,999 | 1.9% | 937 |\n| Putnam | 42.0% | 19,575 | 56.6% | 26,356 | 1.4% | 632 |\n| Fulton | 41.4% | 9,202 | 56.6% | 12,570 | 2.0% | 443 |\n| Delaware | 41.2% | 8,724 | 56.5% | 11,958 | 2.3% | 484 |\n| Herkimer | 41.2% | 11,675 | 56.6% | 16,024 | 2.2% | 611 |\n| Tioga | 40.6% | 9,694 | 57.6% | 13,762 | 1.9% | 446 |\n| Schuyler | 40.1% | 3,445 | 57.7% | 4,960 | 2.2% | 185 |\n| Greene | 39.9% | 8,933 | 58.0% | 12,996 | 2.1% | 469 |\n| Lewis | 39.9% | 4,546 | 58.1% | 6,624 | 2.0% | 227 |\n| Cattaraugus | 39.4% | 13,514 | 58.5% | 20,051 | 2.0% | 697 |\n| Yates | 39.3% | 4,205 | 58.9% | 6,309 | 1.8% | 197 |\n| Schoharie | 38.7% | 5,630 | 59.0% | 8,591 | 2.3% | 336 |\n| Livingston | 38.4% | 11,504 | 59.2% | 17,729 | 2.4% | 715 |\n| Wayne | 38.1% | 15,709 | 60.0% | 24,709 | 1.9% | 782 |\n| Genesee | 37.5% | 10,331 | 60.6% | 16,725 | 1.9% | 524 |\n| Orleans | 36.0% | 5,959 | 62.3% | 10,317 | 1.8% | 297 |\n| Steuben | 34.3% | 14,523 | 63.8% | 26,980 | 1.8% | 781 |\n| Allegany | 34.1% | 6,566 | 63.9% | 12,310 | 2.0% | 394 |\n| Wyoming | 33.8% | 6,134 | 64.7% | 11,745 | 1.6% | 285 |\n| Hamilton | 31.0% | 1,145 | 67.0% | 2,475 | 2.0% | 72 |\n\n\nQuestion\nwhat is the different of votes between both in orange county\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"15695"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-415",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4196.csv` in your code execution environment.\n\nTable Title: Kathrin Hölzl\nTable Content:\n| Season | Date | Location | Discipline | Place |\n| --- | --- | --- | --- | --- |\n| 2007 | 18 Mar 2007 | Lenzerheide, Switzerland | Giant Slalom | 2nd |\n| 2009 | 10 Jan 2009 | Maribor, Slovenia | Giant Slalom | 3rd |\n| 2010 | 28 Nov 2009 | Aspen, USA | Giant Slalom | 1st |\n| 2010 | 28 Dec 2009 | Lienz, Austria | Giant Slalom | 1st |\n| 2010 | 24 Jan 2010 | Cortina d'Ampezzo, Italy | Giant Slalom | 3rd |\n| 2010 | 11 Mar 2010 | Garmisch, Germany | Giant Slalom | 2nd |\n| 2011 | 23 Oct 2010 | Sölden, Austria | Giant Slalom | 2nd |\n| 2011 | 27 Nov 2010 | Aspen, USA | Giant Slalom | 3rd |\n| 2011 | 28 Dec 2010 | Semmering, Austria | Giant Slalom | 3rd |\n\n\nQuestion\nwhat is the total number of her 2nd place finishes on the list?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"3"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4196",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-554.csv` in your code execution environment.\n\nTable Title: Power-to-weight ratio\nTable Content:\n| Capacitor type | Capacity | Volts | Temp. | Energy-to-weight ratio | Power-to-weight ratio |\n| --- | --- | --- | --- | --- | --- |\n| ACT Premlis Lithium ion capacitor | 2000 F | 4.0 V | 25 °C | 54 kJ/kg to 2.0 V | 44.4 W/kg @ 5 A |\n| ACT Premlis Lithium ion capacitor | 2000 F | 4.0 V | 25 °C | 31 kJ/kg to 2.0 V | 850 W/kg @ 10 A |\n| Nesccap Electric double-layer capacitor | 5000 F | 2.7 V | 25 °C | 19.58 kJ/kg to 1.35 V | 5.44 W/kg C/1 (1.875 A) |\n| Nesccap Electric double-layer capacitor | 5000 F | 2.7 V | 25 °C | 5.2 kJ/kg to 1.35 V | 5,200 W/kg @ 2,547A |\n| EEStor EESU barium titanate supercapacitor | 30.693 F | 3500 V | 85 °C | 1471.98 kJ/kg | 80.35 W/kg C/5 |\n| EEStor EESU barium titanate supercapacitor | 30.693 F | 3500 V | 85 °C | 1471.98 kJ/kg | 8,035 W∕kg 20 C |\n| General Atomics 3330CMX2205 High Voltage Capacitor | 20.5 mF | 3300 V | ? °C | 2.3 kJ/kg | 6.8 MW/kg @ 100 kA |\n\n\nQuestion\nwhich one is previous from eesu\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Nesccap Electric double-layer capacitor"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-554",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-9576.csv` in your code execution environment.\n\nTable Title: Bhanumathi Ramakrishna\nTable Content:\n| Year | Film | Language | Character | Co-Star | Music | Banner |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1939 | Vara Vikrayam | Telugu | Kalindi | Chittor V. Nagaiah | Prabhala Satyanarayana | East India Film Company |\n| 1940 | Malathi Madhavam | Telugu | | | | East India Film Company |\n| 1941 | Bhaktimala | Telugu | Radha | | | Bhaskar Films |\n| 1941 | Dharmapatni | Tamil | | | | Famous Films |\n| 1941 | Dharmapatni | Telugu | | | | Famous Films |\n| 1943 | Garuda Garvabhangam | Telugu | | | | Pratiba |\n| 1943 | Krishna Prema | Telugu | Chandravali | | Galipenchala Narasimha Rao | Famous Films & Star Combines |\n| 1944 | Tahsildar | Telugu | Kamala | | | |\n| 1945 | Swargaseema | Telugu | Subbi/Sujatha Devi | Chittor V. Nagaiah | Chittor V. Nagaiah | Vijaya Studios |\n| 1946 | Gruhapravesam | Telugu | Janaki | | | Sarati Films |\n| 1947 | Ratnamala | Telugu | Ratnamala | C. S. R. Anjaneyulu | C. R. Subburaman | Bharani Pictures |\n| 1948 | Raja Mukthi | Tamil | Kannika | M. K. Thyagaraja Bhagavathar | C. R. Subburaman | Narendra Pictures |\n| 1949 | Laila Majnu | Telugu | Laila | A. Nageswara Rao | C. R. Subburaman | Bharani Pictures |\n| 1949 | Laila Majnu | Tamil | Laila | A. Nageswara Rao | C. R. Subburaman | Bharani Pictures |\n| 1949 | Nallathambi | Tamil | Pushpa | N. S. Krishnan | C. R. Subburaman | NSK Films & Uma Pictures |\n| 1949 | Raksharekha | Telugu | Princess Kalavathi | A. Nageswara Rao | Ogirala Ramachandra Rao & H. R. Padmanabha Sastri | |\n| 1949 | Devamanohari | Tamil | Devamanohari | C. Honnappa Bhagavathar | G. Ramanathan | Arkays Pictures |\n| 1949 | Apoorva Sagodharargal | Tamil | Kanchana | M. K. Radha | S. Rajeswara Rao | Gemini Studios |\n| 1949 | Apoorva Sahodaralu | Telugu | Ranjana | M. K. Radha | S. Rajeswara Rao | Gemini Studios |\n| 1949 | Nishaan | Hindi | Kanchana | M. K. Radha | S. Rajeswara Rao | Gemini Studios |\n| 1949 | Rathnakumar | Tamil | | P. U. Chinnappa Bhagavathar | G. Ramanathan & C. R. Subburaman | Murugan Talkies |\n| 1950 | Maya Rambha | Telugu | | | | |\n| 1951 | Malleeswari | Telugu | Malleeswari | N. T. Rama Rao | Adepalli Rama Rao & S. Rajeswara Rao | Vijaya Studios |\n| 1951 | Mangala | Telugu | Mangala | | | Gemini Studios |\n| 1951 | Mangala | Hindi | Mangala | | | Gemini Studios |\n| 1952 | Prema | Telugu | Mothi | A. Nageswara Rao | C. R. Subburaman | Bharani Pictures |\n| 1952 | Kadhal | Tamil | Mothi | A. Nageswara Rao | C. R. Subburaman | Bharani Pictures |\n| 1952 | Rani | Tamil | | S. Balachander | C. R. Subburaman | Jupiter Pictures |\n| 1952 | Rani | Hindi | | Anoop Kumar | C. R. Subburaman | Jupiter Pictures |\n| 1953 | Chandirani | Tamil | Champa & Chandi | N. T. Rama Rao | C. R. Subburaman, Assistants: M. S. Viswanathan & T. K. Ramamoorthy | Bharani Pictures |\n| 1953 | Chandirani | Telugu | Champa & Chandi | N. T. Rama Rao | C. R. Subburaman, Assistants: M. S. Viswanathan & T. K. Ramamoorthy | Bharani Pictures |\n| 1953 | Chandirani | Hindi | Champa & Chandi | Dilip Kumar | C. R. Subburaman, Assistants: M. S. Viswanathan & T. K. Ramamoorthy | Bharani Pictures |\n| 1954 | Aggi Ramudu | Telugu | Saradha | N. T. Rama Rao | S. M. Subbaiah Naidu | Pakshiraja Studios |\n| 1954 | Malaikkallan | Tamil | Poonkothai | M. G. Ramachandran | S. M. Subbaiah Naidu | Pakshiraja Studios |\n| 1954 | Chakrapani | Telugu | Granddaughter | A. Nageswara Rao | P. Bhanumathi | |\n| 1955 | Vipranarayana | Telugu | Devadevi | A. Nageswara Rao | S. Rajeswara Rao | Bharani Pictures |\n| 1955 | Vipranarayana | Tamil | Devadevi | A. Nageswara Rao | S. Rajeswara Rao | Bharani Pictures |\n| 1955 | Kalvanin Kadhali | Tamil | Kalyani | Sivaji Ganesan | G. Govindarajulu Naidu & Ghantasala | Revathi Productions |\n| 1956 | Alibabavum Narpadhu Thirudargalum | Tamil | Marjina | M. G. Ramachandran | S. Dakshinamurthy | Modern Theatres |\n| 1956 | Alibaba 40 Dongalu | Telugu | Marjina | M. G. Ramachandran | S. Dakshinamurthy | Modern Theatres |\n| 1956 | Chintamani | Telugu | Chintamani | | | |\n| 1956 | Madurai Veeran | Tamil | Princess Bommi | M. G. Ramachandran | G. Ramanathan | Krishna Pictures |\n| 1956 | Rangoon Radha | Tamil | Rangam | Sivaji Ganesan | T. R. Papa | Mekala Pictures |\n| 1956 | Tenali Ramakrishna | Telugu | Rangasaani | N. T. Rama Rao & A. Nageswara Rao | Viswanathan Ramamoorthy | Vikram Productions |\n| 1956 | Tenali Raman | Tamil | Krishnasani | N. T. Rama Rao & Sivaji Ganesan | Viswanathan Ramamoorthy | Vikram Productions |\n| 1956 | Sadharam | Tamil | Sadharam | Gemini Ganesan & K. R. Ramaswamy | G. Ramanathan | Kasturi Films |\n| 1956 | Thaaikkuppin Thaaram | Tamil | Sivakami | M. G. Ramachandran | K. V. Mahadevan | Devar Films |\n| 1956 | Rambaiyin Kaadhal | Tamil | Ramba | K. A. Thangavelu | T. R. Papa | Kalpana Pictures |\n| 1957 | Makkalai Petra Magarasi | Tamil | Rangamma | Sivaji Ganesan | K. V. Mahadevan | Sri Lakshmi Pictures |\n| 1957 | Manamagan Thevai | Tamil | | Sivaji Ganesan | G. Ramanathan | Bharani Pictures |\n| 1957 | Varudu Kavali | Telugu | | K. Jaggaiah | G. Ramanathan | Bharani Pictures |\n| 1957 | Rani Lalithangi | Tamil | | Sivaji Ganesan | G. Ramanathan | TNR Productions |\n| 1957 | Ambikapathy | Tamil | Princess Amaravati | Sivaji Ganesan | G. Ramanathan | ALS Productions |\n| 1957 | Nala Damayanti | Telugu | Damayanthi | Kemparaj Urs | | |\n| 1957 | Sarangadhara | Telugu | Chitrangi Devi | N. T. Rama Rao | G. Ramanathan | Minerva Pictures |\n| 1958 | Sarangadhara | Tamil | Chitrangi Devi | Sivaji Ganesan | G. Ramanathan | Minerva Pictures |\n| 1958 | Nadodi Mannan | Tamil | Madhana | M. G. Ramachandran | S. M. Subbaiah Naidu | Emgeeyar Pictures |\n| 1959 | Manimekalai | Tamil | Manimekalai | T. R. Mahalingam | G. Ramanathan | Shekhar Art Film |\n| 1960 | Raja Bakthi | Tamil | Maharasai | Sivaji Ganesan, Vyjayanthimala | G. Govindarajulu Naidu | Revathi Productions |\n| 1960 | Raja Desingu | Tamil | Ranibhai | M. G. Ramachandran | G. Ramanathan | Krishna Pictures |\n| 1961 | Batasari | Telugu | Madhavi | A. Nageswara Rao | Master Venu | Bharani Pictures |\n| 1961 | Kaanal Neer | Tamil | Madhavi | A. Nageswara Rao | Master Venu | Bharani Pictures |\n| 1962 | Annai | Tamil | Savithri | S. V. Ranga Rao | R. Sudharsanam | AVM Productions |\n| 1963 | Kalai Arasi | Tamil | Vani & Valli | M. G. Ramachandran | K. V. Mahadevan | Sarodi Brothers |\n| 1963 | Anuragam | | | | | |\n| 1963 | Arivaali | Tamil | Manorama | Sivaji Ganesan | S. V. Venkatraman | A. T. K. Productions |\n| 1963 | Penchina Prema | Telugu | | | | |\n| 1963 | Kaanchi Thalaivan | Tamil | | M. G. Ramachandran | K. V. Mahadevan | Mekala Pictures |\n| 1964 | Bobbili Yudham | Telugu | Mallamma | N. T. Rama Rao | S. Rajeswara Rao | |\n| 1964 | Vivaha Bandham | Telugu | Bharati | | | |\n| 1965 | Antastulu | Telugu | | A. Nageswara Rao | K. V. Mahadevan | |\n| 1965 | Todu Needa | Telugu | | | | |\n| 1966 | Palnati Yudham | Telugu | Nagamma | N. T. Rama Rao | S. Rajeswara Rao | Sri Anuroopa Films |\n| 1967 | Grihalakshmi | Telugu | Laxmi | | | |\n| 1967 | Pattatthu Rani | Tamil | | Gemini Ganesan | T. K. Ramamoorthy | |\n| 1968 | Poovum Pottum | Tamil | Padmavathi | S. V. Ranga Rao | R. Govardhanam | Vasu Films |\n| 1971 | Mattilo Manikyam | Telugu | Lalitha | | | |\n| 1972 | Anta Mana Manchike | Telugu | Savitri | | | |\n| 1973 | Kattila Thottila | Tamil | | Gemini Ganesan | | Arul Films |\n| 1973 | Vichitra Vivaham | | | | | |\n| 1974 | Ammayi Pelli | Telugu | | | | |\n| 1974 | Tatamma Kala | Telugu | | | | |\n| 1975 | Ippadiyum Oru Penn | Tamil | | | | |\n| 1975 | Pathu Maadha Bandham | Tamil | S. A. Asokan | Krishnan-Panju | | |\n| 1977 | Manavadi Kosam | Telugu | | | | |\n| 1984 | Mangamma Gari Manavadu | Telugu | Mangamma | | | |\n| 1986 | Muddula Manavaraalu | Telugu | | | | |\n| 1986 | Kannukku Mai Ezhuthu | Tamil | | Sujatha, Sarath Babu | Ilaiyaraaja | |\n| 1988 | Attagaru Swagatham | Telugu | | | | |\n| 1990 | Bamma Maata Bangaru Baata | Telugu | Bamma | | | |\n| 1992 | Chamanthi | Telugu | Bhuvaneswari | | | |\n| 1992 | Peddarikam | Telugu | Adusumilli Basavapunnamma | | | |\n| 1992 | Samrat Ashok | Telugu | | | | |\n| 1992 | Chembaruthi | Tamil | | Prashanth, Roja | Ilaiyaraaja | Motherland Movies |\n| 1998 | Pelli Kanuka | Telugu | Savithramma | | | |\n\n\nQuestion\nwhat was the name of the last movie the actress appeared in?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Pelli Kanuka"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-9576",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-3111.csv` in your code execution environment.\n\nTable Title: Franz Liszt's treatments of the works of other composers\nTable Content:\n| Original work | Liszt work | Forces | Date | S no. | Notes |\n| --- | --- | --- | --- | --- | --- |\n| Opera Lucrezia Borgia (1833) | Reminiscences de Lucrezia Borgia | piano | 1840 | S.400 | The sections are: (1) Trio du second acte and (2) Fantaisie sur des motifs favoris de l'opéra: Chanson à boire (Orgie), Duo and Finale |\n| Opera Lucia di Lammermoor (1835) | Reminiscences de Lucia di Lammermoor | piano | 1835‑36 | S.397 | Based on the Sextet |\n| Opera Lucia di Lammermoor (1835) | Marche et cavatine de Lucie de Lammermoor | piano | 1835‑36 | S.398 | Intended as part of the Reminiscences (S.397) but separated by the publisher |\n| Lucia di Lammermoor | Valse à capriccio sur deux motifs de Lucia et Parisina | piano | 1842 | S.401 | Combines motifs from Lucia di Lammermoor and Parisina. The Valse à capriccio, S.401 was revised as No. 3 of 3 Caprices-Valses, S.214 (1850–52). |\n| Opera Parisina (1833) | Valse à capriccio sur deux motifs de Lucia et Parisina | piano | 1842 | S.401 | Combines motifs from Lucia di Lammermoor and Parisina. The Valse à capriccio, S.401 was revised as No. 3 of 3 Caprices-Valses, S.214 (1850–52). |\n| Nuits d'été à Pausilippe, 12 ariettas and nocturnes (voices and chamber ensemble; 1836):\\n\\nNo. 1, \"Barcajuolo\"\\nNo. 9, \"L'Alito di Bice\"\\nNo. 4, \"La Torre di Biasone\" | Nuits d'été à Pausilippe | piano | 1838 | S.399 | |\n| Opera La favorite (1840):\\n\\nDuettino (Act IV) | Spirito gentil | piano | 1847 | S.400a | Possibly same as S.742. |\n| Opera Dom Sébastien (1843):\\n\\nFuneral march | Marche funèbre de Dom Sébastien | piano | 1844 | S.402 | |\n| Act IV | Paraphrase | piano | ? | S.744 | Lost; this was based on Theodor Kullak's transcription (paraphrase), Op. 31, which was itself dedicated to Liszt. |\n| \"Duettino\" | Transcription | piano | ? | S.742 | Lost. Possibly same as S.400a. |\n\n\nQuestion\nwas opera dom sebastien of opera la favorite published in 1844?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"yes"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-3111",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-12691.csv` in your code execution environment.\n\nTable Title: Novi Sad raid\nTable Content:\n| Place | Total | Men | Women | Children | Elderly | Serbs | Jews | Romani | Rusyns | Hungarians | Russians |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| Bečej | 215 | 111 | 72 | 13 | 19 | 102 | 110 | - | - | - | - |\n| Vilovo | 64 | 44 | 6 | 8 | 6 | 64 | - | - | - | - | - |\n| Gardinovci | 37 | 32 | 3 | - | 2 | 37 | - | - | - | - | - |\n| Gospođinci | 85 | 47 | 19 | 15 | 4 | 73 | 10 | - | 2 | - | - |\n| Đurđevo | 223 | 107 | 60 | 41 | 15 | 173 | 22 | - | 27 | - | - |\n| Žabalj | 666 | 355 | 141 | 101 | 69 | 614 | 28 | 23 | - | 1 | - |\n| Lok | 47 | 46 | - | - | 1 | 46 | - | - | - | 1 | - |\n| Mošorin | 205 | 94 | 41 | 44 | 26 | 170 | - | 34 | - | 1 | - |\n| Novi Sad | 1,246 | 489 | 415 | 165 | 177 | 375 | 809 | - | 2 | 18 | 15 |\n| Srbobran | 3 | 3 | - | - | - | 2 | 2 | - | - | - | - |\n| Temerin | 48 | 14 | 15 | 7 | 12 | 6 | 42 | - | - | - | - |\n| Titel | 51 | 45 | - | 1 | 5 | 49 | 1 | - | - | - | - |\n| Čurug | 893 | 554 | 153 | 82 | 104 | 842 | 44 | 7 | - | - | - |\n| Šajkaš | 26 | 24 | 2 | - | - | 25 | 1 | - | - | - | - |\n| All places | 3,809 | 1,965 | 927 | 477 | 440 | 2,578 | 1,068 | 64 | 31 | 21 | 15 |\n\n\nQuestion\nwhich place has the most women?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Novi Sad"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-12691",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4421.csv` in your code execution environment.\n\nTable Title: Parnelli Jones\nTable Content:\n| Year | Car | Start | Qual | Rank | Finish | Laps | Led | Retired |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 1961 | 98 | 5 | 146.080 | 7 | 12 | 192 | 27 | Flagged |\n| 1962 | 98 | 1 | 150.370 | 1 | 7 | 200 | 120 | Running |\n| 1963 | 98 | 1 | 151.153 | 1 | 1 | 200 | 167 | Running |\n| 1964 | 98 | 4 | 155.099 | 4 | 23 | 55 | 7 | Pit fire |\n| 1965 | 98 | 5 | 158.625 | 5 | 2 | 200 | 0 | Running |\n| 1966 | 98 | 4 | 162.484 | 4 | 14 | 87 | 0 | Wheel Bearing |\n| 1967 | 40 | 6 | 166.075 | 6 | 6 | 196 | 171 | Bearing |\n| Totals | Totals | Totals | Totals | Totals | Totals | 1130 | 492 | |\n\n\nQuestion\nin how many indy 500 races, has jones been flagged?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"1"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4421",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-13978.csv` in your code execution environment.\n\nTable Title: Svetoslav Todorov\nTable Content:\n| # | Date | Venue | Opponent | Score | Result | Competition |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1. | 29 March 2000 | Vasil Levski National Stadium, Sofia | Belarus | 1–0 | 4–1 | Friendly |\n| 2. | 7 October 2000 | Georgi Asparuhov Stadium, Sofia | Malta | 3–0 | 3–0 | 2002 World Cup qualifier |\n| 3. | 27 March 2003 | Stadion Mladost, Kruševac | Serbia and Montenegro | 2–1 | 2–1 | Friendly |\n| 4. | 7 June 2003 | Vasil Levski National Stadium, Sofia | Belgium | 2–2 | 2–2 | Euro 2004 qualifier |\n| 5. | 12 November 2005 | Vasil Levski National Stadium, Sofia | Georgia | 5–0 | 6–2 | Friendly |\n| 6. | 12 November 2005 | Vasil Levski National Stadium, Sofia | Georgia | 6–2 | 6–2 | Friendly |\n| 7. | 9 May 2006 | Nagai Stadium, Osaka | Japan | 1–0 | 2–1 | 2006 Kirin Cup |\n\n\nQuestion\nwho was the opponent after georgia?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Japan"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-13978",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-5925.csv` in your code execution environment.\n\nTable Title: IWGP Heavyweight Championship\nTable Content:\n| Rank | Wrestler | No. of reigns | Combined\\ndefenses | Combined\\ndays |\n| --- | --- | --- | --- | --- |\n| 1 | Keiji Mutoh | 4 | 19 | 1,238 |\n| 2 | Hiroshi Tanahashi | 6 | 27 | 1,237 |\n| 3 | Shinya Hashimoto | 3 | 20 | 1,052 |\n| 4 | Tatsumi Fujinami | 6 | 13 | 785 |\n| 5 | Kensuke Sasaki | 5 | 9 | 647 |\n| 6 | Yuji Nagata | 2 | 12 | 570 |\n| 7 | Kazuchika Okada† | 2 | 10 | 556+ |\n| 8 | Kazuyuki Fujita | 3 | 3 | 478 |\n| 9 | Big Van Vader | 3 | 4 | 451 |\n| 10 | Shinsuke Nakamura | 3 | 9 | 390 |\n| 11 | Riki Chōshū | 3 | 5 | 383 |\n| 12 | Antonio Inoki | 1 | 4 | 325 |\n| 13 | Brock Lesnar | 1 | 3 | 280 |\n| 14 | Hiroyoshi Tenzan | 4 | 2 | 197 |\n| 15 | Yoshihiro Takayama | 1 | 3 | 185 |\n| 16 | Satoshi Kojima | 2 | 2 | 168 |\n| 17 | Togi Makabe | 1 | 3 | 161 |\n| 18 | Scott Norton | 2 | 4 | 126 |\n| 19 | Nobuhiko Takada | 1 | 1 | 116 |\n| 20 | Bob Sapp | 1 | 1 | 66 |\n| 21 | Salman Hashimikov | 1 | 0 | 48 |\n| 21 | Tadao Yasuda | 1 | 1 | 48 |\n| 23 | Manabu Nakanishi | 1 | 0 | 45 |\n| 24 | Masahiro Chono | 1 | 0 | 44 |\n| 25 | Genichiro Tenryu | 1 | 0 | 25 |\n\n\nQuestion\neach of these wrestlers came from a reign of 3\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Shinya Hashimoto",
"Kazuyuki Fujita",
"Big Van Vader",
"Shinsuke Nakamura",
"Riki Chōshū"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-5925",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-13836.csv` in your code execution environment.\n\nTable Title: 1998 Marlboro Grand Prix of Miami\nTable Content:\n| Pos | No | Driver | Team | Laps | Time/Retired | Grid | Points |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | 6 | Michael Andretti | Newman-Haas Racing | 150 | 1:33:39.268 | 8 | 20+1 |\n| 2 | 99 | Greg Moore | Forsythe Racing | 150 | +0.075 | 1 | 16+1 |\n| 3 | 1 | Alex Zanardi | Chip Ganassi Racing | 150 | +0.918 | 6 | 14 |\n| 4 | 11 | Christian Fittipaldi | Newman-Haas Racing | 150 | +3.359 | 4 | 12 |\n| 5 | 20 | Scott Pruett | Patrick Racing | 150 | +5.257 | 12 | 10 |\n| 6 | 40 | Adrián Fernández | Patrick Racing | 150 | +5.926 | 5 | 8 |\n| 7 | 5 | Gil de Ferran | Walker Racing | 150 | +6.810 | 11 | 6 |\n| 8 | 8 | Bryan Herta | Team Rahal | 150 | +9.866 | 16 | 5 |\n| 9 | 27 | Dario Franchitti | Team KOOL Green | 150 | +10.275 | 13 | 4 |\n| 10 | 17 | Maurício Gugelmin | PacWest Racing Group | 150 | +10.855 | 10 | 3 |\n| 11 | 33 | Patrick Carpentier | Forsythe Racing | 150 | +11.382 | 9 | 2 |\n| 12 | 18 | Mark Blundell | PacWest Racing Group | 150 | +29.029 | 7 | 1 |\n| 13 | 10 | Richie Hearn | Della Penna Motorsports | 149 | +1 Lap | 15 | |\n| 14 | 9 | JJ Lehto | Hogan Racing | 149 | +1 Lap | 29 | |\n| 15 | 15 | Roberto Moreno | Project Indy | 149 | +1 Lap | 23 | |\n| 16 | 12 | Jimmy Vasser | Chip Ganassi Racing | 148 | +2 Laps | 3 | |\n| 17 | 3 | André Ribeiro | Marlboro Team Penske | 148 | +2 Laps | 2 | |\n| 18 | 36 | Alex Barron | All American Racing | 148 | +2 Laps | 27 | |\n| 19 | 7 | Bobby Rahal | Team Rahal | 147 | +3 Laps | 17 | |\n| 20 | 98 | P. J. Jones | All American Racing | 146 | +4 Laps | 26 | |\n| 21 | 77 | Arnd Meier | Davis Racing | 136 | +14 Laps | 28 | |\n| 22 | 2 | Al Unser, Jr. | Marlboro Team Penske | 122 | Transmission | 14 | |\n| 23 | 24 | Hiro Matsushita | Arciero-Wells Racing | 121 | Contact | 24 | |\n| 24 | 16 | Hélio Castro-Neves | Bettenhausen Racing | 97 | Contact | 22 | |\n| 25 | 34 | Dennis Vitolo | Payton/Coyne Racing | 90 | Withdrew | 25 | |\n| 26 | 25 | Max Papis | Arciero-Wells Racing | 83 | Wheel Bearing | 20 | |\n| 27 | 26 | Paul Tracy | Team KOOL Green | 79 | Suspension | 21 | |\n| 28 | 19 | Michel Jourdain Jr. | Payton/Coyne Racing | 78 | Handling | 19 | |\n| 29 | 21 | Tony Kanaan | Tasman Motorsports Group | 32 | Contact | 18 | |\n\n\nQuestion\nhow many teams competed in the 1998 marlboro grand prix of miami?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"29"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-13836",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-2493.csv` in your code execution environment.\n\nTable Title: Shooting at the 1988 Summer Olympics – Women's 50 metre rifle three positions\nTable Content:\n| Rank | Athlete | Qual | Final | Total | Notes |\n| --- | --- | --- | --- | --- | --- |\n| | Silvia Sperber (FRG) | 590 | 95.6 | 685.6 | OR |\n| | Vesela Letcheva (BUL) | 583 | 100.2 | 683.2 | |\n| | Valentina Cherkasova (URS) | 586 | 95.4 | 681.4 | |\n| 4 | Katja Klepp (GDR) | 584 | 96.5 | 680.5 | |\n| 5 | Sharon Bowes (CAN) | 584 | 96.5 | 680.5 | |\n| 6 | Anna Maloukhina (URS) | 585 | 93.4 | 678.4 | |\n| 7 | Launi Meili (USA) | 582 | 94.5 | 676.5 | |\n| 8 | Anita Karlsson (SWE) | 583 | 93.4 | 676.4 | |\n\n\nQuestion\nwhich runners ran above 95.4?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Silvia Sperber (FRG)",
"Vesela Letcheva (BUL)",
"Katja Klepp (GDR)",
"Sharon Bowes (CAN)"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-2493",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-3586.csv` in your code execution environment.\n\nTable Title: List of Royal Military College of Canada people\nTable Content:\n| Year | Number | Name | Year | Number | Name | Year | Number | Name |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 1884–1885 | 7 | Lukin Homphrey Irving (first) | 1886–1887 | 18 | Duncan MacPherson | 1888 | 4 | William Mahlon Davis |\n| 1889–1890 | 6 | Septimus Julius Augustus Denison | 1891 | 10 | Victor Brereton Rivers | 1892 | 86 | Reuben Wells Leonard |\n| 1893–1894 | 37 | E.H. Drury | 1895–1896 | 15 | Francis Joseph Dixon | 1897 | 48 | A.K. Kirkpatrick |\n| 1898 | 57 | H.S. Greenwood | 1899 | 14 | John Bray Cochrane | 1900 | 41 | Robert Cartwright |\n| 1901 | 154 | F.M. Gaudet | 1902 | 47 | Ernest Frederick Wurtele | 1903 | 21 | A.E. Doucet |\n| 1904 | 82 | Wallace Bruce Matthews Carruthers | 1905 | 188 | W.A.H. Kerr | 1906 | 186 | V.A.S. Williams |\n| 1907 | 139 | C.R.F. Coutlee | 1908 | 232 | John Houlison | 1909 | 91 | J.D. Gibson |\n| 1910 | 63 | George Hooper | 1911 | 255 | H.A. Panet | 1912 | 246 | Major-General Sir Henry Edward Burstall |\n| 1913 | 268 | Henry Robert Visart de Bury et de Bocarmé | 1914; 1919 | 299 | Col. Harry J. Lamb DSO, VD | 1920 | 293 | C.J. Armstrong |\n| 1920–1922 | 392 | W.B. Kingsmill | 1923 | 377 | A.C. Caldwell | 1924 | 140 | G.S. Cartwright |\n| 1925 | 499 | Edouard de B. Panet | 1926 | 631 | A.B. Gillies | 1927 | 623 | S.B. Coristine |\n| 1928 | 555 | R.R. Carr-Harris | 1929 | 667 | E.G. Hanson | 1929–1930 | SUO | G.D. de S. Wotherspoon |\n| 1930–1931 | 1119 | J.H. Price | 1932 | 472 | A.R. Chipman | 1933–1934 | 805 | Colin W. G. Gibson |\n| 1935 | 727 | D.A. White | 1936–1937 | 877 | G.L. Magann | 1938–1939 | 1003 | A.M. Mitchell |\n| 1940–1941 | 803 | J.V. Young | 1942–1943 | 1141 | W.H. O'Reilly | 1944 | 698 | Everett Bristol |\n| 1945 | 982 | D.W. MacKeen | 1946 | 1841 | D.G. Cunningham | 1947 | 1230 | S.H. Dobell |\n| 1948 | 1855 | Ian S. Johnston | 1949 | 1625 | J.D. Watt | 1950 | 1542 | E.W. Crowe |\n| 1951 | 1860 | Nicol Kingsmill | 1952 | 1828 | Ted G.E. Beament | 1953 | 1620 | R.R. Labatt |\n| 1954 | 1766 | Ken H. Tremain | 1955 | 1474 | de L.H.M Panet | 1956 | 2034 | Paul Y. Davoud |\n| 1957 | 1954 | W.P. Carr | 1960 | 1379 | H.A. Mackenzie | 1961 | 2157 | J.H.R. Gagnon |\n| 1962 | 2183 | James E. Pepall | 1963 | 2336 | J.H. Moore | 1964 | 2351 | Guy Savard |\n| 1965 | 2749 | James B. Cronyn | 1966 | 2601 | J. Fergus Maclaren | 1967 | 2791 | Jean P.W. Ostiguy |\n| 1968–1969 | RCNC90 | John F. Frank | 1975–1976 | 3661 | Terry Yates | 1976–1977 | 5533 | Glenn Allen |\n| 1977–1978 | 3172 | Marshall Soule | 1980–1981 | 3251 | Jim Tremain | 1981–1982 | 2897 | Herb Pitts |\n| 1986–1987 | 5604 | Ken Smee | 1987–1988 | 3010 | Peter McLoughlin | 1992–1993 | H3356 | Robin Cumine |\n| 1993–1994 | 5244 | Tony Downs | 1994–1995 | H7543 | Senator Joseph A. Day | 1995–1996 | 5739 | Andre Costin |\n| 1996–1997 | 3550 | Murray Johnston | 1997–1998 | 8813 | John D. Gibson | 1998–1999 | G0055 | Valerie Keyes (first female) |\n| 1999–2000 | 8833 | John Leggat | 2000–2001 | 5758 | Michael Morres | 2001–2002 | 16461 | Ian MacKinnon |\n| 2002–2003 | 6777 | Michel Charron | 2003–2004 | 7776 | Chris Lythgo | 2004–2005 | 7943 | J. William K. Lye |\n| 2005–2006 | 10080 | Robert Booth | 2007–2008 | 6776 | Tim Sparling | 2008–2009 | 15988 | Jeff Kearns |\n| 2010 | 16412 | Gord Clarke | 2011 | 19307 | David Benoit | 2012 | 9889 | Robert Benn |\n| 2013 | M0058 | Marc Drolet (first UTPNCM) | | | | | | |\n\n\nQuestion\nhow many club presidents held their position in the 19th century?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"4"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-3586",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4899.csv` in your code execution environment.\n\nTable Title: Neha Sharma\nTable Content:\n| Year | Film | Role | Language | Notes |\n| --- | --- | --- | --- | --- |\n| 2007 | Chirutha | Sanjna | Telugu | Debut Telugu Film |\n| 2009 | Kurradu | Hema | Telugu | |\n| 2010 | Crook: It's Good To Be Bad | Suhani | Hindi | Debut Hindi Film |\n| 2012 | Teri Meri Kahaani | Meera | Hindi | Special Appearance |\n| 2012 | Kyaa Super Kool Hain Hum | Simran | Hindi | |\n| 2013 | Jayantabhai Ki Luv Story | Simran | Hindi | |\n| 2013 | Yamla Pagla Deewana 2 | Suman | Hindi | |\n| 2014 | Youngistaan | Anwita Chauhan | Hindi | |\n\n\nQuestion\nwhat film game before ter meri kahaani?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Crook: It's Good To Be Bad"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4899",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-13437.csv` in your code execution environment.\n\nTable Title: Pillow Pal\nTable Content:\n| Name | Animal Type | Introduced | Reintroduced | Retired | Beanie Baby Resembled |\n| --- | --- | --- | --- | --- | --- |\n| Antlers | Moose | | 1999 (neon) | 1999 | Chocolate |\n| Baba | Lamb | | 1999 (neon) | 1999 | Fleece |\n| Bruiser | Bulldog | 1997 | | | Wrinkles |\n| Carrots | Bunny | | 1999 (neon) | 1999 | Ears, but pink instead of brown |\n| Chewy | | | 1999 (neon) | 1999 | |\n| Clover | Bunny | 1998 | | | Ears, but white instead of brown |\n| Foxy | Fox | | | | Sly |\n| Glide | Porpoise | | | | Echo the Dolphin |\n| Huggy | Bear | 1995 | 1999 (neon) | 1999 | Cubbie, but yellow instead of brown |\n| Meow | Cat | 1997 | 1999 (neon) | 1999 | Snip |\n| Moo | Cow | 1995 | | | Daisy, but with white body instead of black |\n| Oink | Pig | 1995 | | | Squealer |\n| Paddles | Platypus | | 1999 (neon) | 1999 | Patti |\n| Purr | Tiger | | | | Stripes, but yellow-orange instead of orange-black |\n| Red | Bull | | | | Snort |\n| Ribbit (All-Green) | Frog | 1995 | 1999 (neon) | 1999 | Legs |\n| Ribbit (Green-Yellow) | Frog | | | | Smoochy |\n| Sherbert | Tie-Dye Bear | 1998 | 1999 (neon) | 1999 | Sammy |\n| Snap (All-Yellow) | Turtle | 1995 | | | Speedy, but yellow instead of green |\n| Snap (Yellow-Green) | Turtle | | 1999 (neon) | | Peekaboo |\n| Snuggy | Bear | 1995 | | | Cubbie, but pink instead of brown |\n| Sparkler | Bear | | | 1999 | Spangle |\n| Speckles | Leopard | | | | Freckles |\n| Spotty | Dalmatian | | | | Dotty |\n| Squirt | Elephant | | 1999 (neon) | 1999 | Peanut |\n| Swinger | Monkey | | 1999 (neon) | 1999 | Bongo |\n| Tide | Whale | | | | Splash |\n| Tubby | Hippopotamus | | | | Happy |\n| Woof | Dog | 1995 | 1999 (neon) | 1999 | Bones |\n| Zulu | Zebra | | | | Ziggy, but pink-green instead of black-white |\n\n\nQuestion\nwhat is the name of the pillow pal listed after clover?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Foxy"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-13437",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-5586.csv` in your code execution environment.\n\nTable Title: Wikimania\nTable Content:\n| Conference | Date | Place | attendance | Archive of presentations |\n| --- | --- | --- | --- | --- |\n| Wikimania 2005 | August 5–7 | Frankfurt, Germany | 380 | slides, video |\n| Wikimania 2006 | August 4–6 | Cambridge, United States | 400 | slides and papers, video |\n| Wikimania 2007 | August 3–5 | Taipei, ROC (Taiwan) | 440 | Commons gallery |\n| Wikimania 2008 | July 17–19 | Alexandria, Egypt | 650 | abstracts, slides,video |\n| Wikimania 2009 | August 26–28 | Buenos Aires, Argentina | 559 | slides, video |\n| Wikimania 2010 | July 9–11 | Gdańsk, Poland | about 500 | slides |\n| Wikimania 2011 | August 4–7 | Haifa, Israel | 720 | presentations, video |\n| Wikimania 2012 | July 12–15 | Washington, D.C., United States | 1,400 | presentations, videos |\n| Wikimania 2013 | August 7–11 | Hong Kong | 700 | presentations, videos |\n| Wikimania 2014 | August 6–10 | London, United Kingdom | N/A | |\n\n\nQuestion\nwhere was the conference held the year after buenos aires, argentina?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Gdańsk, Poland"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-5586",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-1127.csv` in your code execution environment.\n\nTable Title: Smile! (Vitas album)\nTable Content:\n| Track number | Russian title | English title | Music | Lyrics |\n| --- | --- | --- | --- | --- |\n| 01 | Улыбнись | Smile! | Vitas | D. Plachkovsky |\n| 02 | Блаженный Гуру | Blessed Guru | Vitas | Vitas |\n| 03 | Восковые фигуры | Wax Figures | Vitas | D. Plachkovsky, Vitas, S. Pudovkin |\n| 04 | Плачет чужая тоска | Someone's Melancholy Is Crying | Vitas | D. Plachovsky |\n| 05 | Аве Мария | Ave Maria | Franz Schubert | Traditional prayer |\n| 06 | Холодный мир | The Cold World | V. Molchanov | D. Plachkovsky |\n| 07 | Остров затонувших кораблей | The Island Of Sunken Ships | O. Gazmanov | E. Nebylova |\n| 08 | Фантастические сны | Fantastic Dreams | Vitas | Vitas, D. Plachkovsky |\n| 09 | Good-bye | Good-bye | Vitas | Vitas |\n| 10 | Счастье | Happiness | Vitas | Vitas |\n| 11 | Отцвели хризантемы | Chrysanthemums Have Faded Out | N. Harito | V. Shumsky |\n| 12 | Дождь в Тбилиси | Rain in Tbilisi | Vitas | Ratner |\n| 13 | Слепой художник | Blind Painter | Vitas | D. Plachkovsky, Vitas, S. Pudovkin |\n| 14 | Милая музыка | Lovely Music | Vitas | Vitas |\n| 15 | Белоруссия | Byelorussia | Alexandra Pakhmutova | N. Dobronravov |\n| 16 | До свидания | See You Later (Do Svidaniya) | Vitas | Vitas |\n\n\nQuestion\nwhich lyricist has the largest amount of tracks?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Vitas"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-1127",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-11317.csv` in your code execution environment.\n\nTable Title: IFK Visby\nTable Content:\n| Season | Level | Division | Section | Position | Movements |\n| --- | --- | --- | --- | --- | --- |\n| 1999 | Tier 5 | Division 4 | Gotland | 6th | Vårserier (Spring Series) |\n| | Tier 5 | Division 4 | Gotland | 5th | Höstserier (Autumn Series) |\n| 2000 | Tier 5 | Division 4 | Gotland | 2nd | Vårserier (Spring Series) |\n| | Tier 5 | Division 4 | Uppland/Gotland Höst | 10th | Höstserier (Autumn Series) |\n| 2001 | Tier 5 | Division 4 | Gotland | 4th | Vårserier (Spring Series) |\n| | Tier 5 | Division 4 | Gotland | 4th | Slutspel A (Playoff A) |\n| 2002 | Tier 5 | Division 4 | Gotland | 3rd | Promotion Playoffs |\n| 2003 | Tier 5 | Division 4 | Gotland | 6th | |\n| 2004 | Tier 5 | Division 4 | Gotland | 4th | |\n| 2005 | Tier 5 | Division 4 | Gotland | 1st | |\n| 2006* | Tier 5 | Division 3 | Östra Svealand | 12th | Relegated |\n| 2007 | Tier 6 | Division 4 | Gotland | 2nd | |\n| 2008 | Tier 6 | Division 4 | Gotland | 3rd | |\n| 2009 | Tier 6 | Division 4 | Gotland | 7th | |\n| 2010 | Tier 6 | Division 4 | Gotland | 2nd | |\n| 2011 | Tier 6 | Division 4 | Gotland | 4th | |\n\n\nQuestion\nwhat is the total number of times that the team finished in 3rd position or higher?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"6"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-11317",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-2000.csv` in your code execution environment.\n\nTable Title: Electoral system of Australia\nTable Content:\n| Seat | State | Majority | Member | Party |\n| --- | --- | --- | --- | --- |\n| HINKLER | Qld | 00.0 | Paul Neville | NPA |\n| SOLOMON | NT | 00.1 | Dave Tollner | Lib |\n| ADELAIDE | SA | 00.2 | Hon Trish Worth | Lib |\n| CANNING | WA | 00.4 | Don Randall | Lib |\n| DOBELL | NSW | 00.4 | Ken Ticehurst | Lib |\n| PARRAMATTA | NSW | 01.1 | Ross Cameron | Lib |\n| McEWEN | Vic | 01.2 | Fran Bailey | Lib |\n| PATERSON | NSW | 01.4 | Bob Baldwin | Lib |\n| HERBERT | Qld | 01.6 | Peter Lindsay | Lib |\n| RICHMOND | NSW | 01.6 | Hon Larry Anthony | NPA |\n| DEAKIN | Vic | 01.7 | Philip Barresi | Lib |\n| EDEN-MONARO | NSW | 01.7 | Gary Nairn | Lib |\n| HINDMARSH | SA | 01.9 | Hon Christine Gallus | Lib |\n\n\nQuestion\nwhat was the total majority that the dobell seat had?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"00.4"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-2000",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-8986.csv` in your code execution environment.\n\nTable Title: Connors–McEnroe rivalry\nTable Content:\n| Year | Tournament | Surface | Round | Winner | Score |\n| --- | --- | --- | --- | --- | --- |\n| 1991 | Basel | Hard | S | John McEnroe | 6–1, 6–3 |\n| 1989 | Toulouse | Hard | F | Jimmy Connors | 6–3, 6–3 |\n| 1987 | Montreal / Toronto | Hard | Q | Jimmy Connors | 6–3, 3–6, 6–3 |\n| 1986 | San Francisco | Carpet | F | John McEnroe | 7–6, 6–3 |\n| 1985 | Montreal / Toronto | Hard | S | John McEnroe | 6–2, 6–3 |\n| 1985 | Chicago | Carpet | F | John McEnroe | W/O |\n| 1984 | US Open | Hard | S | John McEnroe | 6–4, 4–6, 7–5, 4–6, 6–3 |\n| 1984 | Montreal / Toronto | Hard | S | John McEnroe | 2–6, 6–2, 6–3 |\n| 1984 | Wimbledon | Grass | F | John McEnroe | 6–1, 6–1, 6–2 |\n| 1984 | London, Queen's Club | Grass | S | John McEnroe | 6–2, 6–2 |\n| 1984 | Roland Garros | Clay | S | John McEnroe | 7–5, 6–1, 6–2 |\n| 1984 | Dallas WCT | Carpet | F | John McEnroe | 6–1, 6–2, 6–3 |\n| 1983 | Wembley | Carpet | F | John McEnroe | 7–5, 6–1, 6–4 |\n| 1983 | Cincinnati | Hard | S | John McEnroe | 6–7, 6–1, 6–4 |\n| 1983 | London, Queen's Club | Grass | F | Jimmy Connors | 6–3, 6–3 |\n| 1982 | San Francisco | Carpet | F | John McEnroe | 6–1, 6–3 |\n| 1982 | Wimbledon | Grass | F | Jimmy Connors | 3–6, 6–3, 6–7, 7–6, 6–4 |\n| 1982 | London, Queen's Club | Grass | F | Jimmy Connors | 7–5, 6–3 |\n| 1982 | Philadelphia | Carpet | F | John McEnroe | 6–3, 6–3, 6–1 |\n| 1981 | New York City | Carpet | RR | John McEnroe | 6–2, 7–5 |\n| 1981 | Wembley | Carpet | F | Jimmy Connors | 3–6, 2–6, 6–3, 6–4, 6–2 |\n| 1980 | US Open | Hard | S | John McEnroe | 6–4, 5–7, 0–6, 6–3, 7–6 |\n| 1980 | Wimbledon | Grass | S | John McEnroe | 6–3, 3–6, 6–3, 6–4 |\n| 1980 | Dallas WCT | Carpet | F | Jimmy Connors | 2–6, 7–6, 6–1, 6–2 |\n| 1980 | Memphis | Carpet | F | John McEnroe | 7–6, 7–6 |\n| 1980 | Philadelphia | Carpet | F | Jimmy Connors | 6–3, 2–6, 6–3, 3–6, 6–4 |\n| 1979 | US Open | Hard | S | John McEnroe | 6–3, 6–3, 7–5 |\n| 1979 | Dallas WCT | Carpet | S | John McEnroe | 6–1, 6–4, 6–4 |\n| 1979 | Las Vegas | Hard | S | Jimmy Connors | 7–5, 6–4 |\n| 1979 | Pepsi Grand Slam | Clay | S | Jimmy Connors | 6–3, 6–4 |\n| 1978 | Masters | Carpet | RR | John McEnroe | 7–5, 3–0 RET |\n| 1978 | US Open | Hard | S | Jimmy Connors | 6–2, 6–2, 7–5 |\n| 1978 | Indianapolis | Clay | Q | Jimmy Connors | 3–6, 6–1, 6–1 |\n| 1977 | Boston | Clay | R32 | Jimmy Connors | 5–7, 6–2, 7–5 |\n| 1977 | Wimbledon | Grass | S | Jimmy Connors | 6–3, 6–3, 4–6, 6–4 |\n\n\nQuestion\nwhat is the total number of carpet surfaces used?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"13"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-8986",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-3151.csv` in your code execution environment.\n\nTable Title: 2009 Utah Utes football team\nTable Content:\n| Date | Time | Opponent# | Rank# | Site | TV | Result | Attendance |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| September 3 | 7:00 PM | Utah State* | #19 | Rice–Eccles Stadium • Salt Lake City, UT (Battle of the Brothers) | The mtn. | W 35–17 | 45,333 |\n| September 12 | 8:30 PM | at San Jose State* | #17 | Spartan Stadium • San José, CA | ESPNU | W 24–14 | 23,684 |\n| September 19 | 1:30 PM | at Oregon* | #18 | Autzen Stadium • Eugene, OR | ESPN | L 24–31 | 58,017 |\n| September 26 | 5:30 PM | Louisville* | | Rice–Eccles Stadium • Salt Lake City, UT | CBSCS | W 30–14 | 45,588 |\n| October 10 | 4:00 PM | at Colorado State | | Hughes Stadium • Fort Collins, CO | The mtn. | W 24–17 | 30,499 |\n| October 17 | 8:00 PM | at UNLV | #24 | Sam Boyd Stadium • Las Vegas, NV | The mtn. | W 35–15 | 26,315 |\n| October 24 | 2:00 PM | Air Force | #19 | Rice–Eccles Stadium • Salt Lake City, UT | Versus | W 23–16 OT | 45,129 |\n| October 31 | 6:00 PM | Wyoming | #19 | Rice–Eccles Stadium • Salt Lake City, UT | The mtn. | W 22–10 | 44,837 |\n| November 7 | 4:00 PM | New Mexico | #17 | Rice–Eccles Stadium • Salt Lake City, UT (The Bowl) | The mtn. | W 45–14 | 45,051 |\n| November 14 | 5:30 PM | at #4 TCU | #16 | Amon G. Carter Stadium • Fort Worth, TX | CBSCS | L 28–55 | 50,307 |\n| November 21 | 2:00 PM | San Diego State | #23 | Rice–Eccles Stadium • Salt Lake City, UT | Versus | W 38–7 | 44,991 |\n| November 28 | 3:00 PM | at #18 BYU | #22 | LaVell Edwards Stadium • Provo, UT (The Holy War) | CBSCS/The mtn. | L 23–26 OT | 64,301 |\n| December 23 | 6:00 PM | vs. California* | #23 | Qualcomm Stadium • San Diego, CA (Poinsettia Bowl) | ESPN | W 37–27 | 32,665 |\n\n\nQuestion\nagainst what opponent did utah score the largest amount of points?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"New Mexico"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-3151",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-4857.csv` in your code execution environment.\n\nTable Title: 2008 Malaysian motorcycle Grand Prix\nTable Content:\n| Pos | No | Rider | Manufacturer | Laps | Time | Grid | Points |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | 46 | Valentino Rossi | Yamaha | 21 | 43:06.007 | 2 | 25 |\n| 2 | 2 | Dani Pedrosa | Honda | 21 | +4.008 | 1 | 20 |\n| 3 | 4 | Andrea Dovizioso | Honda | 21 | +8.536 | 6 | 16 |\n| 4 | 69 | Nicky Hayden | Honda | 21 | +8.858 | 4 | 13 |\n| 5 | 56 | Shinya Nakano | Honda | 21 | +10.583 | 15 | 11 |\n| 6 | 1 | Casey Stoner | Ducati | 21 | +13.640 | 7 | 10 |\n| 7 | 65 | Loris Capirossi | Suzuki | 21 | +15.936 | 8 | 9 |\n| 8 | 5 | Colin Edwards | Yamaha | 21 | +18.802 | 5 | 8 |\n| 9 | 7 | Chris Vermeulen | Suzuki | 21 | +23.174 | 11 | 7 |\n| 10 | 14 | Randy de Puniet | Honda | 21 | +25.516 | 9 | 6 |\n| 11 | 21 | John Hopkins | Kawasaki | 21 | +27.609 | 10 | 5 |\n| 12 | 13 | Anthony West | Kawasaki | 21 | +41.399 | 13 | 4 |\n| 13 | 50 | Sylvain Guintoli | Ducati | 21 | +45.617 | 16 | 3 |\n| 14 | 15 | Alex de Angelis | Honda | 21 | +49.003 | 17 | 2 |\n| 15 | 24 | Toni Elias | Ducati | 21 | +59.139 | 19 | 1 |\n| 16 | 33 | Marco Melandri | Ducati | 21 | +1:03.328 | 14 | |\n| 17 | 9 | Nobuatsu Aoki | Suzuki | 21 | +1:48.363 | 18 | |\n| Ret | 48 | Jorge Lorenzo | Yamaha | 12 | Accident | 3 | |\n| Ret | 52 | James Toseland | Yamaha | 2 | Accident | 12 | |\n\n\nQuestion\ndid any country have consecutive winners in the race?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"no"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-4857",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-10472.csv` in your code execution environment.\n\nTable Title: Luis Regueiro\nTable Content:\n| # | Date | Venue | Opponent | Score | Result | Competition |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1. | 30 May 1928 | Olympic Stadium (Amsterdam), Amsterdam, Netherland | Mexico | 1–0 | 7–1 | 1928 Summer Olympics |\n| 2. | 30 May 1928 | Olympic Stadium (Amsterdam), Amsterdam, Netherland | Mexico | 3–0 | 7–1 | 1928 Summer Olympics |\n| 3. | 22 June 1930 | Bologna, Italy | Italy | 1–0 | 3–2 | Friendly |\n| 4. | 22 June 1930 | Bologna, Italy | Italy | 3–1 | 3–2 | Friendly |\n| 5. | 13 December 1931 | Dublin, Ireland | Ireland | 3–0 | 5–0 | Friendly |\n| 6. | 13 December 1931 | Dublin, Ireland | Ireland | 5–0 | 5–0 | Friendly |\n| 7. | 24 April 1932 | Oviedo, Spain | Yugoslavia | 1–0 | 2–1 | Friendly |\n| 8. | 21 June 1933 | Madrid, Spain | Bulgaria | 8–0 | 13–0 | Friendly |\n| 9. | 21 June 1933 | Madrid, Spain | Bulgaria | 12–0 | 13–0 | Friendly |\n| 10. | 11 March 1934 | Madrid, Spain | Portugal | 4–0 | 9–0 | 1934 World Cup Qualifier |\n| 11. | 11 March 1934 | Madrid, Spain | Portugal | 6–0 | 9–0 | 1934 World Cup Qualifier |\n| 12. | 21 June 1934 | Firenze, Italy | Italy | 1–0 | 1–1 | 1934 FIFA World Cup |\n| 13. | 24 January 1935 | Madrid, Spain | Bulgaria | 1–0 | 2–0 | Friendly |\n| 14. | 19 January 1936 | Madrid, Spain | Austria | 2–4 | 4–5 | Friendly |\n| 15. | 19 January 1936 | Madrid, Spain | Austria | 4–4 | 4–5 | Friendly |\n| 16. | 23 February 1936 | Barcelona, Spain | Germany | 1–2 | 1–2 | Friendly |\n\n\nQuestion\nhow many consecutive 'friendly' games did spain have?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"11"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-10472",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-10931.csv` in your code execution environment.\n\nTable Title: 1960 Buffalo Bills season\nTable Content:\n| Week | Date | Opponent | Result | Game site | Attendance |\n| --- | --- | --- | --- | --- | --- |\n| 1 | September 11, 1960 | at New York Titans | L 27–3 | Polo Grounds | 10,200 |\n| 2 | September 18, 1960 | Denver Broncos | L 27–21 | War Memorial Stadium | 15,229 |\n| 3 | September 23, 1960 | at Boston Patriots | W 13–0 | Nickerson Field | 20,732 |\n| 4 | October 2, 1960 | Los Angeles Chargers | L 24–10 | War Memorial Stadium | 15,821 |\n| 6 | October 16, 1960 | New York Titans | L 17–13 | War Memorial Stadium | 14,988 |\n| 7 | October 23, 1960 | Oakland Raiders | W 38–9 | War Memorial Stadium | 8,876 |\n| 8 | October 30, 1960 | Houston Oilers | W 25–24 | War Memorial Stadium | 23,001 |\n| 9 | November 6, 1960 | Dallas Texans | L 45–28 | War Memorial Stadium | 19,610 |\n| 10 | November 13, 1960 | at Oakland Raiders | L 20–7 | Kezar Stadium | 8,800 |\n| 11 | November 20, 1960 | at Los Angeles Chargers | W 32–3 | Los Angeles Memorial Coliseum | 16,161 |\n| 12 | November 27, 1960 | at Denver Broncos | T 38–38 | Bears Stadium | 7,785 |\n| 13 | December 4, 1960 | Boston Patriots | W 38–14 | War Memorial Stadium | 14,335 |\n| 14 | December 11, 1960 | at Houston Oilers | L 31–23 | Jeppesen Stadium | 25,243 |\n| 15 | December 18, 1960 | at Dallas Texans | L 24–7 | Cotton Bowl | 18,000 |\n\n\nQuestion\nhow many games had at least 10,000 people in attendance?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"11"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-10931",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-9035.csv` in your code execution environment.\n\nTable Title: 1961–62 Segunda División\nTable Content:\n| Position | Club | Played | Points | Wins | Draws | Losses | Goals for | Goals against | Goal Difference |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| 1 | Córdoba CF | 30 | 40 | 16 | 8 | 6 | 48 | 22 | +26 |\n| 2 | CD Málaga | 30 | 38 | 14 | 10 | 6 | 52 | 36 | +16 |\n| 3 | Granada CF | 30 | 36 | 15 | 6 | 9 | 48 | 34 | +14 |\n| 4 | UD Las Palmas | 30 | 35 | 15 | 5 | 10 | 47 | 39 | +8 |\n| 5 | Recreativo de Huelva | 30 | 33 | 13 | 7 | 10 | 43 | 42 | +1 |\n| 6 | Levante UD | 30 | 32 | 14 | 4 | 12 | 49 | 42 | +7 |\n| 7 | Hércules CF | 30 | 32 | 14 | 4 | 12 | 55 | 46 | +9 |\n| 8 | Real Murcia | 30 | 31 | 12 | 7 | 11 | 40 | 35 | +5 |\n| 9 | Real Jaén | 30 | 31 | 14 | 3 | 13 | 58 | 42 | +16 |\n| 10 | Cádiz CF | 30 | 28 | 12 | 4 | 14 | 43 | 52 | -9 |\n| 11 | CD Cartagena | 30 | 28 | 13 | 2 | 15 | 45 | 56 | -11 |\n| 12 | CD Mestalla | 30 | 27 | 11 | 5 | 14 | 50 | 49 | +1 |\n| 13 | Albacete Balompié | 30 | 27 | 10 | 7 | 13 | 27 | 32 | -5 |\n| 14 | CD San Fernando | 30 | 27 | 11 | 5 | 14 | 37 | 47 | -10 |\n| 15 | Atlético Ceuta | 30 | 23 | 8 | 7 | 15 | 33 | 48 | -15 |\n| 16 | CD Villarrobledo | 30 | 12 | 4 | 4 | 22 | 26 | 79 | -53 |\n\n\nQuestion\nwhat were the number of goals for listed for the hercules cf club?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"55"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-9035",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-1104.csv` in your code execution environment.\n\nTable Title: 1988–89 FA Cup\nTable Content:\n| Tie no | Home team | Score | Away team | Date |\n| --- | --- | --- | --- | --- |\n| 1 | Enfield | 1–1 | Leyton Orient | 19 November 1988 |\n| Replay | Leyton Orient | 2–2 | Enfield | 23 November 1988 |\n| Replay | Leyton Orient | 0–1 | Enfield | 28 November 1988 |\n| 2 | Blackpool | 2–1 | Scunthorpe United | 19 November 1988 |\n| 3 | Darlington | 1–2 | Notts County | 19 November 1988 |\n| 4 | Bath City | 2–0 | Grays Athletic | 19 November 1988 |\n| 5 | Bristol City | 3–1 | Southend United | 19 November 1988 |\n| 6 | Burnley | 0–2 | Chester City | 19 November 1988 |\n| 7 | Preston North End | 1–1 | Tranmere Rovers | 19 November 1988 |\n| Replay | Tranmere Rovers | 3–0 | Preston North End | 22 November 1988 |\n| 8 | Yeovil Town | 3–2 | Merthyr Tydfil | 19 November 1988 |\n| 9 | Reading | 4–2 | Hendon | 19 November 1988 |\n| 10 | Woking | 1–4 | Cambridge United | 19 November 1988 |\n| 11 | Gillingham | 3–3 | Peterborough United | 19 November 1988 |\n| Replay | Peterborough United | 1–0 | Gillingham | 23 November 1988 |\n| 12 | Bolton Wanderers | 0–0 | Chesterfield | 19 November 1988 |\n| Replay | Chesterfield | 2–3 | Bolton Wanderers | 28 November 1988 |\n| 13 | Grimsby Town | 1–0 | Wolverhampton Wanderers | 19 November 1988 |\n| 14 | Stafford Rangers | 2–2 | Crewe Alexandra | 19 November 1988 |\n| Replay | Crewe Alexandra | 3–2 | Stafford Rangers | 22 November 1988 |\n| 15 | Scarborough | 2–1 | Stockport County | 19 November 1988 |\n| 16 | Doncaster Rovers | 0–0 | Brandon United | 19 November 1988 |\n| Replay | Doncaster Rovers | 2–1 | Brandon United | 22 November 1988 |\n| 17 | Fulham | 0–1 | Colchester United | 19 November 1988 |\n| 18 | Brentford | 2–0 | Halesowen Town | 19 November 1988 |\n| 19 | Bristol Rovers | 3–0 | Fisher Athletic | 20 November 1988 |\n| 20 | Altrincham | 3–2 | Lincoln City | 19 November 1988 |\n| 21 | Bognor Regis Town | 2–1 | Exeter City | 19 November 1988 |\n| 22 | Huddersfield Town | 1–1 | Rochdale | 19 November 1988 |\n| Replay | Rochdale | 3–4 | Huddersfield Town | 28 November 1988 |\n| 23 | Mansfield Town | 1–1 | Sheffield United | 19 November 1988 |\n| Replay | Sheffield United | 2–1 | Mansfield Town | 22 November 1988 |\n| 24 | Cardiff City | 3–0 | Hereford United | 19 November 1988 |\n| 25 | Halifax Town | 1–0 | York City | 19 November 1988 |\n| 26 | Newport County | 1–2 | Maidstone United | 19 November 1988 |\n| 27 | Southport | 0–2 | Port Vale | 19 November 1988 |\n| 28 | Runcorn | 2–2 | Wrexham | 19 November 1988 |\n| Replay | Wrexham | 2–3 | Runcorn | 22 November 1988 |\n| 29 | Torquay United | 2–2 | Fareham Town | 19 November 1988 |\n| Replay | Fareham Town | 2–3 | Torquay United | 23 November 1988 |\n| 30 | Kettering Town | 2–1 | Dartford | 19 November 1988 |\n| 31 | Rotherham United | 3–1 | Barrow | 19 November 1988 |\n| 32 | Aldershot | 1–0 | Hayes | 19 November 1988 |\n| 33 | Dagenham | 0–4 | Sutton United | 19 November 1988 |\n| 34 | Waterlooville | 1–4 | Aylesbury United | 19 November 1988 |\n| 35 | Telford United | 1–1 | Carlisle United | 19 November 1988 |\n| Replay | Carlisle United | 4–1 | Telford United | 22 November 1988 |\n| 36 | Swansea City | 3–1 | Northampton Town | 19 November 1988 |\n| 37 | Frickley Athletic | 0–2 | Northwich Victoria | 19 November 1988 |\n| 38 | Hartlepool United | 2–0 | Wigan Athletic | 19 November 1988 |\n| 39 | Welling United | 3–0 | Bromsgrove Rovers | 19 November 1988 |\n| 40 | Guisborough Town | 0–1 | Bury | 19 November 1988 |\n\n\nQuestion\nwhat is the number of games that gillingham and peterborough united played in the first round proper?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"2"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-1104",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-2898.csv` in your code execution environment.\n\nTable Title: Bishop of Iceland\nTable Content:\n| # | Name | Birth and death | Office started | Office ended |\n| --- | --- | --- | --- | --- |\n| 1 | Geir Vídalín | 27 October 1761\\n–\\n20 September 1823 | 1801 | 1823 |\n| 2 | Steingrímur Jónsson | | 1824 | 1845 |\n| 3 | Helgi Thordersen | 8 April 1794\\n–\\n4 December 1867 | 1846 | 1866 |\n| 4 | 'Pétur Pétursson | 3 October 1808\\n–\\n15 May 1891 | 1866 | 1889 |\n| 5 | Hallgrímur Sveinsson | 5 April 1841\\n–\\n16 December 1909 | 1889 | 1908 |\n| 6 | Þórhallur Bjarnarson | 2 December 1855\\n–\\n15 December 1916 | 1908 | 1916 |\n| 7 | Jón Helgason | 1866\\n–\\n1942 | 1917 | 1939 |\n| 8 | Sigurgeir Sigurðsson | 3 August 1890\\n-\\n13 October 1953 | 1939 | 1953 |\n| 9 | Ásmundur Guðmundsson | 6 October 1888\\nReykholt\\n–\\n29 May 1969\\nReykjavík | 1954 | 1989 |\n| 10 | Sigurbjörn Einarsson | 30 June 1911\\nVestur-Skaftafellssýsla\\n–\\n28 August 2008\\nReykjavík | 1959 | 1981 |\n| 11 | Pétur Sigurgeirsson\\n(son of Sigurgeir Sigurðsson, 8th Bishop of Iceland) | 2 June 1919\\n–\\n3 June 2010 | 1981 | 1989 |\n| 12 | Ólafur Skúlason | 29 December 1929\\n–\\n9 June 2008 | 1989 | 1997 |\n| 13 | Karl Sigurbjörnsson\\n(son of Sigurbjörn Einarsson, 10th Bishop of Iceland) | 5 February 1947\\nReykjavík | 1998 | 2012 |\n| 14 | Agnes Sigurðardóttir | 19 October 1954\\nÍsafjörður | 24 June 2012 | Incumbent |\n\n\nQuestion\nwhich bishop served between the years of 1846 and 1866?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Helgi Thordersen"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-2898",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-6985.csv` in your code execution environment.\n\nTable Title: List of National Natural Landmarks in Hawaii\nTable Content:\n| | Name | Date | Location | County | Description |\n| --- | --- | --- | --- | --- | --- |\n| 1 | Diamond Head | | Honolulu | Oahu | State Monument |\n| 2 | I'ao Valley | | Wailuku | Maui | State Monument |\n| 3 | Kanaha Pond | June 1971 | Kahului | Maui | Bird Sanctuary |\n| 4 | Koʻolau Range Pali | | | Oahu | |\n| 5 | Makalawena Marsh | June 1972 | North Kona | Hawaiʻi | Bird Sanctuary |\n| 6 | Mauna Kea | November 1972 | Saddle Road | Hawaiʻi | U.S. state high point |\n| 7 | North Shore Cliffs | December 1972 | Molokaʻi | Maui | |\n\n\nQuestion\nother than mauna kea, name a place in hawaii.\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Makalawena Marsh"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-6985",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-9789.csv` in your code execution environment.\n\nTable Title: 2002–03 Edmonton Oilers season\nTable Content:\n| Round | # | Player | Nationality | College/Junior/Club Team (League) |\n| --- | --- | --- | --- | --- |\n| 1 | 15 | Jesse Niinimäki | Finland | Ilves (Finland) |\n| 2 | 31 | Jeff Deslauriers | Canada | Chicoutimi Saguenéens (QMJHL) |\n| 2 | 36 | Jarret Stoll | Canada | Kootenay Ice (WHL) |\n| 2 | 44 | Matt Greene | United States | Green Bay Gamblers (USHL) |\n| 3 | 79 | Brock Radunske | Canada | Michigan State Spartans (NCAA) |\n| 4 | 106 | Ivan Koltsov | Russia | Cherepovets (Russia) |\n| 4 | 111 | Jonas Almtorp | Sweden | Modo Hockey (Sweden) |\n| 4 | 123 | Robin Kovář | Czech Republic | HC Vsetin (Czech.) |\n| 5 | 148 | Glenn Fisher | Canada | Fort Saskatchewan Traders (AJHL) |\n| 6 | 181 | Mikko Luoma | Finland | Tappara (Finland) |\n| 7 | 205 | Jean-Francois Dufort | Canada | Cape Breton Screaming Eagles (QMJHL) |\n| 7 | 211 | Patrick Murphy | Canada | Newmarket Hurricanes (OPJHL) |\n| 8 | 244 | Dwight Helminen | United States | Michigan Wolverines (NCAA) |\n| 8 | 245 | Tomáš Micka | Czech Republic | HC Slavia Praha (Czech.) |\n| 9 | 274 | Fredrik Johansson | Sweden | Frolunda (Sweden) |\n\n\nQuestion\nlist each of the players from finland.\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Jesse Niinimäki",
"Mikko Luoma"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-9789",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-10841.csv` in your code execution environment.\n\nTable Title: 1971 World Figure Skating Championships\nTable Content:\n| Rank | Name | Nation | CP | FP | Points | Placings |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1 | Beatrix Schuba | Austria | 1 | 7 | 2763.0 | 10 |\n| 2 | Julie Lynn Holmes | United States | 2 | 5 | 2697.3 | 24.5 |\n| 3 | Karen Magnussen | Canada | 4 | 2 | 2697.7 | 27 |\n| 4 | Janet Lynn | United States | 5 | 1 | 2680.0 | 34 |\n| 5 | Rita Trapanese | Italy | 3 | 8 | 2623.6 | 47.5 |\n| 6 | Sonja Morgenstern | East Germany | 9 | 3 | 2606.6 | 52 |\n| 7 | Zsuzsa Almássy | Hungary | 6 | 4 | 2599.9 | 57 |\n| 8 | Charlotte Walter | Switzerland | 8 | 14 | 2480.7 | 86 |\n| 9 | Christine Errath | East Germany | 13 | 6 | 2493.5 | 83 |\n| 10 | Suna Murray | United States | 14 | 9 | 2475.0 | 91 |\n| 11 | Elena Alexandrova | Soviet Union | 10 | 13 | 2450.5 | 103 |\n| 12 | Patricia Ann Dodd | United Kingdom | 7 | 16 | | 100 |\n| 13 | Kazumi Yamashita | Japan | 12 | 11 | | 116 |\n| 14 | Ludmila Bezáková | Czechoslovakia | 11 | 15 | | 122 |\n| 15 | Jean Scott | United Kingdom | 15 | 10 | | 132 |\n| 16 | Diane Hall | Canada | 19 | 12 | | 132 |\n| 17 | Anita Johansson | Sweden | 16 | 18 | | 145 |\n| 18 | Judith Bayer | West Germany | 20 | 17 | | 159 |\n| 19 | Ruth Hutchinson | Canada | 17 | 20 | | 168 |\n| 20 | Sonja Balun | Austria | 22 | 19 | | 177 |\n| 21 | Joëlle Cartaux | France | 18 | 22 | | 188 |\n| 22 | Cinzia Frosio | Italy | 21 | 21 | | 197 |\n\n\nQuestion\nwhich woman finished last in the 1971 world figured skating championships?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Cinzia Frosio"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-10841",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-5753.csv` in your code execution environment.\n\nTable Title: 2003 Asian Athletics Championships – Women's triple jump\nTable Content:\n| Rank | Name | Nationality | Result | Notes |\n| --- | --- | --- | --- | --- |\n| | Huang Qiuyan | China | 14.39 | SB |\n| | Anastasiya Juravleva | Uzbekistan | 14.21 | =SB |\n| | Zhang Hao | China | 13.63 | |\n| 4 | Wacharee Ritthiwat | Thailand | 13.54 | SB |\n| 5 | Tatyana Bocharova | Kazakhstan | 13.50 | |\n| 6 | Wang Kuo-Huei | Chinese Taipei | 13.25 | SB |\n| 7 | Fumiyo Yoshida | Japan | 13.09 | |\n| 8 | Ngew Sin Mei | Malaysia | 12.93 | |\n| 9 | Manisha Dey | India | 12.83 | |\n| 10 | Thitima Muangjan | Thailand | 12.79 | |\n| 11 | Phan Thi Thu Lan | Vietnam | 12.75 | |\n| 12 | Lo Yu-Hsin | Chinese Taipei | 12.69 | |\n| | Elena Bobrovskaya | Kyrgyzstan | DNS | |\n\n\nQuestion\nhow many points apart were the 1st place competitor and the 12th place competitor?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"1.7"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-5753",
"task_type": "TQA"
}
|
WTQ
|
[
{
"content": "# Mission\nYou are a reasoning agent that solves problems by thinking and using tools in a multi-turn conversation.\n\n# Core Tags\nYou must use the following XML tags to structure your responses:\n- `<think>`: Your private space for reasoning, planning, and evaluating results.\n- `<tool_call>`: Your request to execute a tool. This tag contains the function name and arguments.\n- `<answer>`: Your final, conclusive answer to the user's question, containing only the required JSON object.\n\n# Interaction Protocol\n1. Your interaction is turn-based. Every response you give must start with a `<think>` tag.\n2. After thinking, you can issue one or more `<tool_call>` tags, or present the final `<answer>`.\n3. Example of a `<tool_call>` for table reasoning:\n\n<tool_call>\n{\"name\": \"python\", \"arguments\": {\"code\": \"import pandas as pd\\ndf = pd.read_csv('my_data.csv')\\nprint(df.head())\", \"files\": [\"my_data.csv\"]}}\n</tool_call>\n\nIMPORTANT: Use print() statements to output any results you want to see, otherwise they won't be visible.\n",
"role": "system"
},
{
"content": "# Role\nYou are an expert AI data analyst, skilled at solving complex, table-based questions by combining deep thought with Python code execution.\n\n# Task\nYour mission is to analyze the provided table file and answer a related question. You must achieve this goal through a sequence of thoughts and actions (tool calls).\n\n# Instructions\nPlease follow these steps rigorously:\n\n## 1. Thought\nIn your first response, you must include this section. You need to:\n- Analyze the Problem: Carefully understand the question's requirements and break it down if it is complex.\n- Plan Your Strategy: Design clear steps to solve the problem. Decide which parts require calculation or data extraction via Python code and which parts require subsequent reasoning based on the code's output.\n- Formulate Code (If needed): If you decide to use a tool, formulate the Python code needed to retrieve the key information for your solution.\n\n## 2. Action and Answer\n- Action: After your 'Thought' process, if required, issue a `<tool_call>` to execute your plan.\n- Answer: After you have gathered enough information through thinking and tool calls, you must, in a separate and subsequent response, output only the `<answer>` tag containing the final answer.\n\n# Table File\nYou will have access to a CSV file named `WTQ_nt-8219.csv` in your code execution environment.\n\nTable Title: 2013 Vattenfall Cyclassics\nTable Content:\n| | Cyclist | Team | Time | UCI World Tour\\nPoints |\n| --- | --- | --- | --- | --- |\n| 1 | John Degenkolb (GER) | Argos-Shimano | 5h 45' 16\" | 80 |\n| 2 | André Greipel (GER) | Lotto-Belisol | s.t. | 60 |\n| 3 | Alexander Kristoff (NOR) | Team Katusha | + 1\" | 50 |\n| 4 | José Joaquín Rojas (ESP) | Movistar Team | + 1\" | 40 |\n| 5 | Elia Viviani (ITA) | Cannondale | + 1\" | 30 |\n| 6 | Boy Van Poppel (NLD) | Vacansoleil-DCM | + 1\" | 22 |\n| 7 | Nikolas Maes (BEL) | Omega Pharma-Quick Step | + 1\" | 14 |\n| 8 | Thor Hushovd (NOR) | BMC Racing Team | + 1\" | 10 |\n| 9 | Matti Breschel (DNK) | Team Saxo-Tinkoff | + 1\" | 6 |\n| 10 | Arnaud Démare (FRA) | FDJ.fr | + 1\" | 2 |\n\n\nQuestion\nwas josé joaquín rojas from the movistar team or team katusha?\n\n\nAnswer Format\nThe final answer should be concise and use the following format:\n<answer>\n```json\n{\n \"answer\": [\n \"answer1\",\n \"answer2\",\n ...\n ]\n}\n```\n</answer>\n",
"role": "user"
}
] |
table_reasoning
|
{
"ground_truth": [
"Movistar Team"
],
"style": "rule"
}
|
{
"id": "WTQ_nt-8219",
"task_type": "TQA"
}
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 20
Size of downloaded dataset files:
22.3 MB
Size of the auto-converted Parquet files:
22.3 MB
Number of rows:
33,609
Models trained or fine-tuned on Jclennon/TableMind-data