Agentic QA 1.0

AndroidWorld Benchmark

A standardized evaluation suite for measuring how effectively AI agents perform real-world tasks within the Android operating system.

How we achieved it?
94.8% Success Rate
116 Total Tasks
110 Success
6 Failed

Benchmark Results

AudioRecorderRecordAudio

AudioRecorderRecordAudioWithFileName

BrowserDraw

BrowserMaze

BrowserMultiply

CameraTakePhoto

CameraTakeVideo

ClockStopWatchPausedVerify

ClockStopWatchRunning

ClockTimerEntry

ContactsAddContact

ContactsNewContactDraft

ExpenseAddMultiple

ExpenseAddMultipleFromGallery

ExpenseAddMultipleFromMarkor

ExpenseAddSingle

ExpenseDeleteDuplicates

ExpenseDeleteDuplicates2

ExpenseDeleteMultiple

ExpenseDeleteMultiple2

ExpenseDeleteSingle

FilesDeleteFile

FilesMoveFile

MarkorCreateFolder

MarkorCreateNote

MarkorCreateNoteAndSms

MarkorCreateNoteFromClipboard

MarkorDeleteAllNotes

MarkorDeleteNewestNote

MarkorDeleteNote

MarkorEditNote

MarkorMoveNote

MarkorTranscribeReceipt

NotesIsTodo

NotesMeetingAttendeeCount

NotesRecipeIngredientCount

NotesTodoItemCount

OpenAppTaskEval

OsmAndFavorite

OsmAndMarker

OsmAndTrack

RecipeAddMultipleRecipes

RecipeAddMultipleRecipesFromImage

RecipeAddMultipleRecipesFromMarkor

RecipeAddMultipleRecipesFromMarkor2

RecipeAddSingleRecipe

RecipeDeleteDuplicateRecipes

RecipeDeleteMultipleRecipes

RecipeDeleteMultipleRecipesWithConstraint

RecipeDeleteMultipleRecipesWithNoise

RecipeDeleteSingleRecipe

RecipeDeleteSingleWithRecipeWithNoise

RetroCreatePlaylist

RetroPlayingQueue

RetroPlaylistDuration

RetroSavePlaylist

SaveCopyOfReceiptTaskEval

SimpleCalendarAddOneEvent

SimpleCalendarAddOneEventInTwoWeeks

SimpleCalendarAddOneEventRelativeDay

SimpleCalendarAddOneEventTomorrow

SimpleCalendarAddRepeatingEvent

SimpleCalendarAnyEventsOnDate

SimpleCalendarDeleteEvents

SimpleCalendarDeleteEventsOnRelativeDay

SimpleCalendarDeleteOneEvent

SimpleCalendarEventOnDateAtTime

SimpleCalendarEventsInNextWeek

SimpleCalendarEventsInTimeRange

SimpleCalendarEventsOnDate

SimpleCalendarFirstEventAfterStartTime

SimpleCalendarLocationOfEvent

SimpleCalendarNextEvent

SimpleCalendarNextMeetingWithPerson

SimpleDrawProCreateDrawing

SimpleSmsReply

SimpleSmsReplyMostRecent

SimpleSmsResend

SimpleSmsSend

SimpleSmsSendClipboardContent

SimpleSmsSendReceivedAddress

SportsTrackerActivitiesCountForWeek

SportsTrackerActivitiesOnDate

SportsTrackerActivityDuration

SportsTrackerLongestDistanceActivity

SportsTrackerTotalDistanceForCategoryOverInterval

SportsTrackerTotalDurationForCategoryThisWeek

SystemBluetoothTurnOff

SystemBluetoothTurnOffVerify

SystemBluetoothTurnOn

SystemBluetoothTurnOnVerify

SystemBrightnessMax

SystemBrightnessMaxVerify

SystemBrightnessMin

SystemBrightnessMinVerify

SystemCopyToClipboard

SystemWifiTurnOff

SystemWifiTurnOffVerify

SystemWifiTurnOn

SystemWifiTurnOnVerify

TasksCompletedTasksForDate

TasksDueNextWeek

TasksDueOnDate

TasksHighPriorityTasks

TasksHighPriorityTasksDueOnDate

TasksIncompleteTasksOnDate

TurnOffWifiAndTurnOnBluetooth

TurnOnWifiAndOpenApp

VlcCreatePlaylist

VlcCreateTwoPlaylists

MarkorAddNoteHeader

MarkorChangeNoteContent

MarkorMergeNotes

MarkorTranscribeVideo

RecipeDeleteDuplicateRecipes2

RecipeDeleteDuplicateRecipes3