id
stringlengths 2
214
| conversations
listlengths 2
42
| data_source
stringclasses 54
values |
|---|---|---|
cauldron/dvqa/images/dvqa_00193617.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 3 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Jury."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Row."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Row."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Jury."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm sound for all the datasets?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm sound in the dataset rest larger than the accuracy of the algorithm jury in the dataset lead?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the blue color represent?"
},
{
"from": "gpt",
"value": "Rest."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm piece in the dataset rest?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Piece."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Rest."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193631.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 9 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Son."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Idea."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Idea."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Risk."
},
{
"from": "human",
"value": "How many total people preferred the object idea across all the categories?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the object desire in the category model preferred by more people than the object son in the category type?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Cent."
},
{
"from": "human",
"value": "How many people prefer the object desire in the category cent?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Son."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Type."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193633.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 30 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Harbor."
},
{
"from": "human",
"value": "What percentage of people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "Is the value of tail in year larger than the value of harbor in arm?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the crimson color represent?"
},
{
"from": "gpt",
"value": "Judge."
},
{
"from": "human",
"value": "What percentage of people prefer the object harbor in the category arm?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Tail."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Year."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193634.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Piece."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Yard."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many objects are liked by more than 2 people?"
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "How many people prefer the objects flow or sitter?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "Is the object beard preferred by less people than author?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many people prefer the object yard?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the eighth bar from the left?"
},
{
"from": "gpt",
"value": "Yard."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Eight."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193641.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 7?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Size."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Coast."
},
{
"from": "human",
"value": "What is the sum of all the values in the size group?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the value of text in pot larger than the value of size in drive?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the forestgreen color represent?"
},
{
"from": "gpt",
"value": "Drive."
},
{
"from": "human",
"value": "What is the value of pot in text?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Text."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Shore."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193646.png
|
[
{
"from": "human",
"value": "How many objects are preferred by less than 50 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Extent."
},
{
"from": "human",
"value": "What percentage of people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Plenty."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Closet."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Beef."
},
{
"from": "human",
"value": "What percentage of people prefer the object drug in the category force?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "What is the label of the seventh group of bars from the left?"
},
{
"from": "gpt",
"value": "Plenty."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Force."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193647.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Coal."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Oil."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 3?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms ten and coal?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm ten larger than coal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm ten?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Oil."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193664.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Lay."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "God."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 20?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm lay larger than god?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm god?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Lay."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193684.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Cross."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Shift."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many objects are liked by less than 1 people?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "How many people prefer the objects cross or city?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "Is the object shift preferred by more people than city?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object city?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Cross."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193685.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 7?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Object."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Gain."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "West."
},
{
"from": "human",
"value": "What is the sum of all the values in the gain group?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Is the value of gain in pass smaller than the value of west in county?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the green color represent?"
},
{
"from": "gpt",
"value": "County."
},
{
"from": "human",
"value": "What is the value of pass in object?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Object."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "County."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193686.png
|
[
{
"from": "human",
"value": "How many items sold more than 9 units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "How many units of items loss and closet were sold?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "Did the item place sold more units than loss?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many units of the item loss were sold?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the left?"
},
{
"from": "gpt",
"value": "Place."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193696.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Pack."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Bomb."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 50?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm pack larger than studio?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm bomb?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Pack."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193699.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 5?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Combat."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Table."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Brush."
},
{
"from": "human",
"value": "What is the sum of all the values in the museum group?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the value of brush in tip smaller than the value of combat in child?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Tip."
},
{
"from": "human",
"value": "What is the value of child in table?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Glance."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Child."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193705.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 8 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Rice."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Ground."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm rice for all the datasets?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm fuel in the dataset guide smaller than the accuracy of the algorithm ground in the dataset self?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the mediumpurple color represent?"
},
{
"from": "gpt",
"value": "Guide."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm rice in the dataset self?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Fuel."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Appeal."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193706.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Cure."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Baby."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many bars have values larger than 1?"
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "What is the sum of the values of driver and knife?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the value of knife smaller than driver?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the value of notice?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Driver."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Seven."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193708.png
|
[
{
"from": "human",
"value": "How many items sold more than 8 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Peace."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Hunger."
},
{
"from": "human",
"value": "How many units of the item number were sold across all the stores?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Did the item vector in the store bench sold larger units than the item number in the store wire?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the blue color represent?"
},
{
"from": "gpt",
"value": "Brand."
},
{
"from": "human",
"value": "How many units of the item vector were sold in the store brand?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Vector."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Form."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Five."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193710.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 90 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Graph."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Color."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Graph."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm color in the dataset powder smaller than the accuracy of the algorithm graph in the dataset pilot?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Powder."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm graph in the dataset powder?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Graph."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Powder."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193721.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Screen."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Row."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 3?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms row and screen?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm screen smaller than author?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm row?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Author."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193724.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 2?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Salary."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Notice."
},
{
"from": "human",
"value": "What is the sum of all the values in the unit group?"
},
{
"from": "gpt",
"value": "18."
},
{
"from": "human",
"value": "Is the value of bread in pile smaller than the value of salary in door?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the indianred color represent?"
},
{
"from": "gpt",
"value": "Sample."
},
{
"from": "human",
"value": "What is the value of pile in salary?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Unit."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Pile."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193733.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 5 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Claim."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm value for all the datasets?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm dancer in the dataset clerk smaller than the accuracy of the algorithm value in the dataset style?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the goldenrod color represent?"
},
{
"from": "gpt",
"value": "Style."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm mile in the dataset clerk?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the second stack of bars from the left?"
},
{
"from": "gpt",
"value": "Value."
},
{
"from": "human",
"value": "What is the label of the second element from the bottom in each stack of bars?"
},
{
"from": "gpt",
"value": "Mold."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many elements are there in each stack of bars?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193738.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 7?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Credit."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "0."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Credit."
},
{
"from": "human",
"value": "Is the value of credit in plot larger than the value of news in table?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Plot."
},
{
"from": "human",
"value": "What is the value of plot in ride?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Guy."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Plot."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Eight."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193744.png
|
[
{
"from": "human",
"value": "How many objects are preferred by less than 90 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Danger."
},
{
"from": "human",
"value": "What percentage of people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Second."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Maid."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Stem."
},
{
"from": "human",
"value": "What percentage of people prefer the object second in the category meat?"
},
{
"from": "gpt",
"value": "40."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Maid."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Bullet."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193745.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Lip."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Mess."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many objects are liked by less than 8 people?"
},
{
"from": "gpt",
"value": "Eight."
},
{
"from": "human",
"value": "How many people prefer the objects hole or ladder?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the object lip preferred by less people than ladder?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object living?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Radio."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Nine."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193746.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 7?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which group of bars contains the largest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Item."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "View."
},
{
"from": "human",
"value": "What is the value of the largest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "0."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "View."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Item."
},
{
"from": "human",
"value": "Is the value of view in denial smaller than the value of item in future?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Future."
},
{
"from": "human",
"value": "What is the value of stem in item?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "View."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Stem."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193747.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 1?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Space."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Lip."
},
{
"from": "human",
"value": "What is the sum of all the values in the input group?"
},
{
"from": "gpt",
"value": "19."
},
{
"from": "human",
"value": "Is the value of lip in grant larger than the value of scale in report?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the forestgreen color represent?"
},
{
"from": "gpt",
"value": "Grant."
},
{
"from": "human",
"value": "What is the value of event in till?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the sixth group of bars from the left?"
},
{
"from": "gpt",
"value": "Till."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Corn."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193751.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 5?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which group of bars contains the largest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Career."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Career."
},
{
"from": "human",
"value": "What is the value of the largest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "-8."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Hour."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Bath."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the orchid color represent?"
},
{
"from": "gpt",
"value": "Movie."
},
{
"from": "human",
"value": "What is the value of movie in bomb?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Career."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Center."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193757.png
|
[
{
"from": "human",
"value": "Which item sold the most units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Debate."
},
{
"from": "human",
"value": "Which item sold the least units?"
},
{
"from": "gpt",
"value": "Combat."
},
{
"from": "human",
"value": "How many units of the the most sold item were sold?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many units of the the least sold item were sold?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many more of the most sold item were sold compared to the least sold item?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "How many items sold less than 7 units?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "How many units of items debate and budget were sold?"
},
{
"from": "gpt",
"value": "16."
},
{
"from": "human",
"value": "Did the item combat sold less units than debate?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many units of the item debate were sold?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom?"
},
{
"from": "gpt",
"value": "Budget."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193762.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Powder."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Motion."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 3?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms motion and powder?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm motion smaller than powder?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm motion?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Motion."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Two."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193764.png
|
[
{
"from": "human",
"value": "How many items sold less than 9 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Prize."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Butter."
},
{
"from": "human",
"value": "How many units of the item point were sold across all the stores?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "Did the item butter in the store hen sold larger units than the item prize in the store arc?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the seagreen color represent?"
},
{
"from": "gpt",
"value": "Status."
},
{
"from": "human",
"value": "How many units of the item stairs were sold in the store height?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the sixth group of bars from the left?"
},
{
"from": "gpt",
"value": "Stairs."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Height."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Six."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193766.png
|
[
{
"from": "human",
"value": "How many items sold more than 3 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Pride."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Silver."
},
{
"from": "human",
"value": "How many units of the item silver were sold across all the stores?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "What store does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Rage."
},
{
"from": "human",
"value": "How many units of the item file were sold in the store rage?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "File."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Valley."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193771.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 3 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Action."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Joy."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm roll for all the datasets?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm roll in the dataset author smaller than the accuracy of the algorithm joy in the dataset wage?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Wage."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm action in the dataset author?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the sixth stack of bars from the left?"
},
{
"from": "gpt",
"value": "Action."
},
{
"from": "human",
"value": "What is the label of the first element from the bottom in each stack of bars?"
},
{
"from": "gpt",
"value": "Wage."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193778.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Tail."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Fly."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "70."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 10?"
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm chief smaller than tail?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm wheel?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Wheel."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193780.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Pain."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Lock."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many bars have values larger than 4?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the values of pain and lock?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Is the value of damage smaller than pain?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of pain?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the left?"
},
{
"from": "gpt",
"value": "Mile."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193781.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 3 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Health."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm fog for all the datasets?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm lack in the dataset public smaller than the accuracy of the algorithm fence in the dataset travel?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Public."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm fog in the dataset public?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the sixth group of bars from the left?"
},
{
"from": "gpt",
"value": "Source."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Travel."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Two."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193783.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 50 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Owner."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Female."
},
{
"from": "human",
"value": "Is the value of stock in rage larger than the value of owner in wave?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What percentage of people prefer the object guilt in the category curve?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Owner."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Wave."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Five."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193784.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Street."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Stick."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 6?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms suite and stick?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm stick larger than girl?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm stick?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the left?"
},
{
"from": "gpt",
"value": "Street."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Seven."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193785.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 20 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Volume."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Volume."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Volume."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "War."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm war in the dataset stress smaller than the accuracy of the algorithm mouth in the dataset jacket?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the olivedrab color represent?"
},
{
"from": "gpt",
"value": "Jacket."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm war in the dataset stress?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Mouth."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Stress."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193787.png
|
[
{
"from": "human",
"value": "Which item sold the most units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Sister."
},
{
"from": "human",
"value": "Which item sold the least units?"
},
{
"from": "gpt",
"value": "Ring."
},
{
"from": "human",
"value": "How many units of the the most sold item were sold?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many units of the the least sold item were sold?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "How many more of the most sold item were sold compared to the least sold item?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many items sold more than 3 units?"
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "How many units of items ring and roof were sold?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "Did the item bride sold less units than roof?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many units of the item roof were sold?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom?"
},
{
"from": "gpt",
"value": "Cry."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Seven."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193789.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Tent."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Pool."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many objects are liked by less than 9 people?"
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "How many people prefer the objects share or pool?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the object dark preferred by more people than pool?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many people prefer the object stick?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom?"
},
{
"from": "gpt",
"value": "Dark."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193797.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 2 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Effort."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Hour."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Driver."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm effort for all the datasets?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm reach in the dataset brain smaller than the accuracy of the algorithm hour in the dataset path?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the crimson color represent?"
},
{
"from": "gpt",
"value": "Path."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm effort in the dataset path?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Driver."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Path."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193803.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Trust."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Bundle."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 60?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm trust smaller than tea?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm tea?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Tea."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193804.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 8 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Dozen."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Pile."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Dozen."
},
{
"from": "human",
"value": "How many total people preferred the object name across all the categories?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Is the object wealth in the category belief preferred by less people than the object wisdom in the category foil?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object wealth in the category belief?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Life."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Foil."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Nine."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193807.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 9 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Plain."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Issue."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Plain."
},
{
"from": "human",
"value": "How many total people preferred the object issue across all the categories?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the object note in the category scheme preferred by more people than the object issue in the category color?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the lightgreen color represent?"
},
{
"from": "gpt",
"value": "Color."
},
{
"from": "human",
"value": "How many people prefer the object plain in the category scheme?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Plain."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Color."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193811.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 6 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Motion."
},
{
"from": "human",
"value": "How many people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Motion."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Fish."
},
{
"from": "human",
"value": "How many total people preferred the object motion across all the categories?"
},
{
"from": "gpt",
"value": "13."
},
{
"from": "human",
"value": "Is the object motion in the category need preferred by more people than the object fish in the category prayer?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Back."
},
{
"from": "human",
"value": "How many people prefer the object fish in the category back?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Fish."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Back."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193814.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 5?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group of bars contains the largest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Safety."
},
{
"from": "human",
"value": "What is the value of the largest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Count."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Safety."
},
{
"from": "human",
"value": "Is the value of count in pencil smaller than the value of appeal in book?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the palevioletred color represent?"
},
{
"from": "gpt",
"value": "Book."
},
{
"from": "human",
"value": "What is the value of pencil in appeal?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Count."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the left in each group?"
},
{
"from": "gpt",
"value": "Book."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193820.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 20?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Course."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Heard."
},
{
"from": "human",
"value": "Is the value of plenty in staff larger than the value of heard in jaw?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the chocolate color represent?"
},
{
"from": "gpt",
"value": "Staff."
},
{
"from": "human",
"value": "What is the value of wind in plenty?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Grip."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Wind."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193824.png
|
[
{
"from": "human",
"value": "How many objects are preferred by less than 20 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Fiber."
},
{
"from": "human",
"value": "What percentage of people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Court."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Roll."
},
{
"from": "human",
"value": "Is the value of court in lip smaller than the value of fiber in excess?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Maid."
},
{
"from": "human",
"value": "What percentage of people prefer the object tray in the category lip?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Court."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Excess."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193826.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Harm."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Meat."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "How many objects are liked by more than 4 people?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "How many people prefer the objects meat or harm?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the object harm preferred by more people than meat?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many people prefer the object harm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the first bar from the bottom?"
},
{
"from": "gpt",
"value": "Meat."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193832.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Spread."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "10000000."
},
{
"from": "human",
"value": "How many bars have values smaller than 10?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the value of sense smaller than hen?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of sense?"
},
{
"from": "gpt",
"value": "10000."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Spread."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193847.png
|
[
{
"from": "human",
"value": "How many items sold less than 2 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which item sold the least units in any shop?"
},
{
"from": "gpt",
"value": "Skirt."
},
{
"from": "human",
"value": "How many units did the worst selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Beam."
},
{
"from": "human",
"value": "How many units of the item roof were sold across all the stores?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Did the item roof in the store youth sold larger units than the item beam in the store flux?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the mediumseagreen color represent?"
},
{
"from": "gpt",
"value": "Youth."
},
{
"from": "human",
"value": "How many units of the item beam were sold in the store youth?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Shell."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Flux."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193848.png
|
[
{
"from": "human",
"value": "How many objects are preferred by less than 3 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Denial."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Favor."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Baby."
},
{
"from": "human",
"value": "How many total people preferred the object minute across all the categories?"
},
{
"from": "gpt",
"value": "13."
},
{
"from": "human",
"value": "Is the object favor in the category escape preferred by less people than the object denial in the category twelve?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the blue color represent?"
},
{
"from": "gpt",
"value": "Twelve."
},
{
"from": "human",
"value": "How many people prefer the object denial in the category trap?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the fifth group of bars from the left?"
},
{
"from": "gpt",
"value": "Minute."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Escape."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193851.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 6 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Mess."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Rest."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Rest."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Mess."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm rest for all the datasets?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm rest in the dataset luxury smaller than the accuracy of the algorithm mess in the dataset profit?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the forestgreen color represent?"
},
{
"from": "gpt",
"value": "Profit."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm basis in the dataset luxury?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Basis."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Luxury."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193852.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 5 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "View."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm vision for all the datasets?"
},
{
"from": "gpt",
"value": "19."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm genius in the dataset manner larger than the accuracy of the algorithm bomb in the dataset note?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the mediumpurple color represent?"
},
{
"from": "gpt",
"value": "Manner."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm rage in the dataset unit?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the sixth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Rage."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Muscle."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Six."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193854.png
|
[
{
"from": "human",
"value": "Which item sold the most units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Campus."
},
{
"from": "human",
"value": "Which item sold the least units?"
},
{
"from": "gpt",
"value": "Love."
},
{
"from": "human",
"value": "How many units of the the most sold item were sold?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many units of the the least sold item were sold?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How many more of the most sold item were sold compared to the least sold item?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many items sold more than 1 units?"
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "How many units of items drama and campus were sold?"
},
{
"from": "gpt",
"value": "17."
},
{
"from": "human",
"value": "How many units of the item amount were sold?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the left?"
},
{
"from": "gpt",
"value": "Sleep."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Eight."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193855.png
|
[
{
"from": "human",
"value": "How many items sold less than 4 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which item sold the least units in any shop?"
},
{
"from": "gpt",
"value": "Play."
},
{
"from": "human",
"value": "How many units did the worst selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Play."
},
{
"from": "human",
"value": "How many units of the item play were sold across all the stores?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Did the item advice in the store cabin sold smaller units than the item grip in the store stake?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the lightskyblue color represent?"
},
{
"from": "gpt",
"value": "Cabin."
},
{
"from": "human",
"value": "How many units of the item grip were sold in the store stake?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Advice."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Cabin."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Two."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193856.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Draft."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Fire."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many objects are liked by more than 6 people?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "How many people prefer the objects draft or yard?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "Is the object turn preferred by less people than yard?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object fire?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the left?"
},
{
"from": "gpt",
"value": "Barn."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193858.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Behalf."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Cereal."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 9?"
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms cereal and county?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm status larger than behalf?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm status?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Status."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193859.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 5 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Trip."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm trip for all the datasets?"
},
{
"from": "gpt",
"value": "16."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm trip in the dataset reply smaller than the accuracy of the algorithm wall in the dataset aim?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Order."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm youth in the dataset reply?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Trip."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Order."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193861.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 3?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Family."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Family."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Loss."
},
{
"from": "human",
"value": "What is the sum of all the values in the loss group?"
},
{
"from": "gpt",
"value": "19."
},
{
"from": "human",
"value": "Is the value of roof in motor smaller than the value of loss in murder?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the palegoldenrod color represent?"
},
{
"from": "gpt",
"value": "Motor."
},
{
"from": "human",
"value": "What is the value of crime in loss?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the fifth group of bars from the left?"
},
{
"from": "gpt",
"value": "Get."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Crime."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193867.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Beef."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Close."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 3?"
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms jazz and camera?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm tape larger than beef?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm extent?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the seventh bar from the left?"
},
{
"from": "gpt",
"value": "Close."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Eight."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193870.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Jail."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Army."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 60?"
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm drunk smaller than army?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm jail?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Jail."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193877.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 1 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Lie."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Yard."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm harm for all the datasets?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm finger in the dataset view smaller than the accuracy of the algorithm lie in the dataset defeat?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Defeat."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm yard in the dataset defeat?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Lie."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "View."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Five."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193889.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Threat."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Air."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 50?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm firm smaller than threat?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm firm?"
},
{
"from": "gpt",
"value": "40."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Air."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193890.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 9 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Focus."
},
{
"from": "human",
"value": "How many total people preferred the object focus across all the categories?"
},
{
"from": "gpt",
"value": "32."
},
{
"from": "human",
"value": "Is the object gyro in the category coat preferred by less people than the object body in the category remark?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Coat."
},
{
"from": "human",
"value": "How many people prefer the object gyro in the category coat?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Focus."
},
{
"from": "human",
"value": "What is the label of the first bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Coat."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193894.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Trap."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Need."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many bars have values larger than 4?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the values of trap and bunk?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the value of need larger than bunk?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the value of self?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Trap."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193898.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Style."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Enemy."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 9?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms style and gown?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm enemy larger than gown?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm good?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Enemy."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193899.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 10?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Snow."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Snow."
},
{
"from": "human",
"value": "Is the value of trap in farm smaller than the value of corn in gain?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the forestgreen color represent?"
},
{
"from": "gpt",
"value": "Lead."
},
{
"from": "human",
"value": "What is the value of gain in snow?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Cold."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Farm."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193901.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Reform."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Start."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "How many bars have values larger than 4?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the values of reform and start?"
},
{
"from": "gpt",
"value": "13."
},
{
"from": "human",
"value": "Is the value of reform larger than start?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of reform?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom?"
},
{
"from": "gpt",
"value": "Start."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193902.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Poet."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Worth."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 5?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms studio and clock?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm studio smaller than poet?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm team?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the left?"
},
{
"from": "gpt",
"value": "Studio."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193911.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Vector."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Combat."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "-8."
},
{
"from": "human",
"value": "How many bars have values smaller than -8?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the value of uncle larger than set?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of vector?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Set."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193914.png
|
[
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Book."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Hat."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "-9."
},
{
"from": "human",
"value": "How many bars have values larger than 9?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the value of paint smaller than voting?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of outfit?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the seventh bar from the left?"
},
{
"from": "gpt",
"value": "Voting."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193927.png
|
[
{
"from": "human",
"value": "How many items sold more than 2 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Guide."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Foot."
},
{
"from": "human",
"value": "How many units of the item foot were sold across all the stores?"
},
{
"from": "gpt",
"value": "26."
},
{
"from": "human",
"value": "Did the item guide in the store lunch sold larger units than the item fruit in the store maid?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Lunch."
},
{
"from": "human",
"value": "How many units of the item guide were sold in the store symbol?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Foot."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Maid."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193930.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Lumber."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Handle."
},
{
"from": "human",
"value": "What percentage of people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "70."
},
{
"from": "human",
"value": "What percentage of people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "How many objects are liked by more than 10 percent of people?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Is the object handle preferred by more people than folk?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What percentage of people prefer the object handle?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Lumber."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193934.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 10000?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Thirty."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Height."
},
{
"from": "human",
"value": "Is the value of height in corps larger than the value of thirty in office?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the grey color represent?"
},
{
"from": "gpt",
"value": "Smoke."
},
{
"from": "human",
"value": "What is the value of cycle in hell?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Liquid."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Smoke."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Five."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193939.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 50 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Grass."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Grass."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the darkturquoise color represent?"
},
{
"from": "gpt",
"value": "Leg."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm grass in the dataset leg?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Grass."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Bag."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193943.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 8 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Folk."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Dark."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Shape."
},
{
"from": "human",
"value": "How many total people preferred the object draft across all the categories?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the object route in the category tire preferred by more people than the object draft in the category plot?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Plot."
},
{
"from": "human",
"value": "How many people prefer the object dark in the category plot?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Dark."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Plot."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193946.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than -9?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Defeat."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Start."
},
{
"from": "human",
"value": "Is the value of defeat in talent larger than the value of art in matter?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the royalblue color represent?"
},
{
"from": "gpt",
"value": "Matter."
},
{
"from": "human",
"value": "What is the value of matter in start?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Art."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Talent."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193951.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 9?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "Which group of bars contains the smallest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Talk."
},
{
"from": "human",
"value": "What is the value of the smallest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "0."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Shop."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "King."
},
{
"from": "human",
"value": "Is the value of shop in code larger than the value of talk in task?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Hen."
},
{
"from": "human",
"value": "What is the value of hen in inside?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Inside."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Task."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193954.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 60 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Lumber."
},
{
"from": "human",
"value": "What percentage of people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Lumber."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Attack."
},
{
"from": "human",
"value": "Is the value of break in jungle larger than the value of lumber in river?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the olivedrab color represent?"
},
{
"from": "gpt",
"value": "Anyone."
},
{
"from": "human",
"value": "What percentage of people prefer the object lumber in the category jungle?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Break."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Jungle."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193956.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Doctor."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Reach."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "30."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 30?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm reach larger than dozen?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm doctor?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Doctor."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193964.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 70?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Record."
},
{
"from": "human",
"value": "Is the value of kid in leg larger than the value of record in square?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Square."
},
{
"from": "human",
"value": "What is the value of ride in kid?"
},
{
"from": "gpt",
"value": "40."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Shame."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the left in each group?"
},
{
"from": "gpt",
"value": "Ride."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193968.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 50?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Way."
},
{
"from": "human",
"value": "Is the value of part in memory larger than the value of throat in horror?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Memory."
},
{
"from": "human",
"value": "What is the value of memory in sitter?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Throat."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Horror."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193972.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 30?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Tube."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "North."
},
{
"from": "human",
"value": "Is the value of tube in draft larger than the value of north in desire?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the powderblue color represent?"
},
{
"from": "gpt",
"value": "Desire."
},
{
"from": "human",
"value": "What is the value of liquor in rage?"
},
{
"from": "gpt",
"value": "70."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "North."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Draft."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193973.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 7 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Vice."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Favor."
},
{
"from": "human",
"value": "How many total people preferred the object favor across all the categories?"
},
{
"from": "gpt",
"value": "19."
},
{
"from": "human",
"value": "Is the object hour in the category plate preferred by more people than the object muscle in the category member?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the green color represent?"
},
{
"from": "gpt",
"value": "Herd."
},
{
"from": "human",
"value": "How many people prefer the object muscle in the category member?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the fifth stack of bars from the left?"
},
{
"from": "gpt",
"value": "Vice."
},
{
"from": "human",
"value": "What is the label of the first element from the bottom in each stack of bars?"
},
{
"from": "gpt",
"value": "Plate."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193982.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 6?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Wall."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Detail."
},
{
"from": "human",
"value": "Is the value of wall in wine larger than the value of pace in cancer?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Result."
},
{
"from": "human",
"value": "What is the value of result in pace?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Tent."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Cancer."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193996.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Shape."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Whisky."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 5?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms shape and whisky?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm pastor larger than shape?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm pastor?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Whisky."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00193998.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Liquor."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Silver."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many objects are liked by less than 6 people?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "How many people prefer the objects start or liquor?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "Is the object liquor preferred by less people than start?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object silver?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Number."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Nine."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194001.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy higher than 40 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Lawyer."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Air."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm air in the dataset hero smaller than the accuracy of the algorithm lawyer in the dataset source?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the mediumpurple color represent?"
},
{
"from": "gpt",
"value": "Neck."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm air in the dataset neck?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Lawyer."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Neck."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194007.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Help."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Year."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 8?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms year and gate?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm clay larger than year?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm title?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the bottom?"
},
{
"from": "gpt",
"value": "Clay."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194015.png
|
[
{
"from": "human",
"value": "How many algorithms have accuracy lower than 3 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Holder."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Weapon."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Weapon."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Holder."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm wheel for all the datasets?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm wheel in the dataset belief smaller than the accuracy of the algorithm holder in the dataset glass?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What dataset does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Limit."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm wheel in the dataset belief?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Holder."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Limit."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Three."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194025.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Agent."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Lunch."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "How many objects are liked by more than 3 people?"
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "How many people prefer the objects stake or agent?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the object act preferred by less people than lunch?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object stake?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the first bar from the bottom?"
},
{
"from": "gpt",
"value": "Agent."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194029.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Meal."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Hurry."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 7?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms strain and meal?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm atom larger than meal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm spirit?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom?"
},
{
"from": "gpt",
"value": "Spirit."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Five."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194031.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Voice."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Sphere."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "40."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "40."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 40?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm sphere smaller than reason?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm reason?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Living."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194032.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 8?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Source."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Hope."
},
{
"from": "human",
"value": "What is the sum of all the values in the hope group?"
},
{
"from": "gpt",
"value": "21."
},
{
"from": "human",
"value": "Is the value of source in floor smaller than the value of show in verse?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the forestgreen color represent?"
},
{
"from": "gpt",
"value": "Floor."
},
{
"from": "human",
"value": "What is the value of floor in source?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Source."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Second."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many groups of bars are there?"
},
{
"from": "gpt",
"value": "Four."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194036.png
|
[
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Farmer."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Scope."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many objects are liked by more than 2 people?"
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "How many people prefer the objects growth or beard?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the object period preferred by less people than lot?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many people prefer the object ball?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the sixth bar from the bottom?"
},
{
"from": "gpt",
"value": "Ball."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194039.png
|
[
{
"from": "human",
"value": "How many objects are preferred by more than 50 percent of people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Grade."
},
{
"from": "human",
"value": "Which object is the least preferred in any category?"
},
{
"from": "gpt",
"value": "Shop."
},
{
"from": "human",
"value": "What percentage of people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What percentage of people like the least preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Shop."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Grade."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Patrol."
},
{
"from": "human",
"value": "What percentage of people prefer the object grade in the category signal?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Shop."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Fence."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194043.png
|
[
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Skill."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Amount."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 2?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms skill and sera?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm amount smaller than phrase?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm amount?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Phrase."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194044.png
|
[
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 8?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Wheel."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Voice."
},
{
"from": "human",
"value": "What is the sum of all the values in the voice group?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "Is the value of wheel in truck larger than the value of speed in knee?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What element does the seagreen color represent?"
},
{
"from": "gpt",
"value": "Truck."
},
{
"from": "human",
"value": "What is the value of knee in output?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Speed."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Truck."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194045.png
|
[
{
"from": "human",
"value": "How many items sold less than 8 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which item sold the least units in any shop?"
},
{
"from": "gpt",
"value": "Genius."
},
{
"from": "human",
"value": "How many units did the worst selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Genius."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Fool."
},
{
"from": "human",
"value": "How many units of the item none were sold across all the stores?"
},
{
"from": "gpt",
"value": "16."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Stuff."
},
{
"from": "human",
"value": "How many units of the item jaw were sold in the store signal?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the fifth group of bars from the left?"
},
{
"from": "gpt",
"value": "None."
},
{
"from": "human",
"value": "What is the label of the third bar from the left in each group?"
},
{
"from": "gpt",
"value": "Path."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
cauldron/dvqa/images/dvqa_00194054.png
|
[
{
"from": "human",
"value": "Which item sold the most units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Agent."
},
{
"from": "human",
"value": "Which item sold the least units?"
},
{
"from": "gpt",
"value": "Spirit."
},
{
"from": "human",
"value": "How many units of the the most sold item were sold?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many units of the the least sold item were sold?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How many more of the most sold item were sold compared to the least sold item?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many items sold less than 5 units?"
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "How many units of items agent and ideal were sold?"
},
{
"from": "gpt",
"value": "13."
},
{
"from": "human",
"value": "Did the item spirit sold less units than vein?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a logarithmic scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many units of the item vein were sold?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the bottom?"
},
{
"from": "gpt",
"value": "Spirit."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] |
dvqa(cauldron,llava_format)
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.