All 116 AndroidWorld tasks
Sorted A–Z. Open a task to watch its recording and step through what the agent did. Filter to the two tasks Google’s original grader reads differently, or to the 5 where Lusor was slower than Mobilerun’s published time.
| Task ↑ | App | Mobilerun’s grader | Google’s grader | Lusor | Mobilerun | Faster | |
|---|---|---|---|---|---|---|---|
| AudioRecorderRecordAudio | Audio Recorder | Pass | Pass | 27.2 s | 147.0 s | 5.4× faster | Audio Recorder27.2 s vs 147.0 sMobilerun’s grader: Pass · Google’s: Pass |
| AudioRecorderRecordAudioWithFileName | Audio Recorder | Pass | Fail, read differently ¹ | 42.3 s | 250.9 s | 5.9× faster | Audio Recorder42.3 s vs 250.9 sMobilerun’s grader: Pass · Google’s: Fail, read differently ¹ |
| BrowserDraw | Browser | Pass | Pass | 90.2 s | 388.0 s | 4.3× faster | Browser90.2 s vs 388.0 sMobilerun’s grader: Pass · Google’s: Pass |
| BrowserMaze | Browser | Pass | Pass | 51.2 s | 350.5 s | 6.8× faster | Browser51.2 s vs 350.5 sMobilerun’s grader: Pass · Google’s: Pass |
| BrowserMultiply ⁶ | Browser | Pass | Pass | 195.2 s | 362.9 s | 1.9× faster | Browser195.2 s vs 362.9 sMobilerun’s grader: Pass · Google’s: Pass |
| CameraTakePhoto | Camera | Pass | Pass | 15.2 s | 199.3 s | 13.1× faster | Camera15.2 s vs 199.3 sMobilerun’s grader: Pass · Google’s: Pass |
| CameraTakeVideo | Camera | Pass | Pass | 84.2 s | 192.9 s | 2.3× faster | Camera84.2 s vs 192.9 sMobilerun’s grader: Pass · Google’s: Pass |
| ClockStopWatchPausedVerify | Clock | Pass | Pass | 21.2 s | 216.7 s | 10.2× faster | Clock21.2 s vs 216.7 sMobilerun’s grader: Pass · Google’s: Pass |
| ClockStopWatchRunning | Clock | Pass | Pass | 18.2 s | 122.1 s | 6.7× faster | Clock18.2 s vs 122.1 sMobilerun’s grader: Pass · Google’s: Pass |
| ClockTimerEntry | Clock | Pass | Pass | 21.1 s | 117.0 s | 5.5× faster | Clock21.1 s vs 117.0 sMobilerun’s grader: Pass · Google’s: Pass |
| ContactsAddContact | Contacts | Pass | Pass | 39.2 s | 409.4 s | 10.4× faster | Contacts39.2 s vs 409.4 sMobilerun’s grader: Pass · Google’s: Pass |
| ContactsNewContactDraft | Contacts | Pass | Pass | 48.2 s | 215.0 s | 4.5× faster | Contacts48.2 s vs 215.0 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseAddMultiple | Pro Expense | Pass | Pass | 72.2 s | 471.1 s | 6.5× faster | Pro Expense72.2 s vs 471.1 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseAddMultipleFromGallery | Pro Expense | Pass | Pass | 96.2 s | 636.8 s | 6.6× faster | Pro Expense96.2 s vs 636.8 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseAddMultipleFromMarkor | Pro Expense | Pass | Fail, read differently ¹ | 126.2 s | 318.7 s | 2.5× faster | Pro Expense126.2 s vs 318.7 sMobilerun’s grader: Pass · Google’s: Fail, read differently ¹ |
| ExpenseAddSingle | Pro Expense | Pass | Pass | 42.2 s | 311.7 s | 7.4× faster | Pro Expense42.2 s vs 311.7 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseDeleteDuplicates | Pro Expense | Pass | Pass | 42.2 s | 418.0 s | 9.9× faster | Pro Expense42.2 s vs 418.0 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseDeleteDuplicates2 | Pro Expense | Pass | Pass | 93.3 s | 382.5 s | 4.1× faster | Pro Expense93.3 s vs 382.5 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseDeleteMultiple | Pro Expense | Pass | Pass | 30.2 s | 271.1 s | 9.0× faster | Pro Expense30.2 s vs 271.1 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseDeleteMultiple2 | Pro Expense | Pass | Pass | 180.3 s | 366.7 s | 2.0× faster | Pro Expense180.3 s vs 366.7 sMobilerun’s grader: Pass · Google’s: Pass |
| ExpenseDeleteSingle | Pro Expense | Pass | Pass | 45.2 s | 155.6 s | 3.4× faster | Pro Expense45.2 s vs 155.6 sMobilerun’s grader: Pass · Google’s: Pass |
| FilesDeleteFile | Files | Pass | Pass | 24.2 s | 204.4 s | 8.4× faster | Files24.2 s vs 204.4 sMobilerun’s grader: Pass · Google’s: Pass |
| FilesMoveFile | Files | Pass | Pass | 51.2 s | 380.8 s | 7.4× faster | Files51.2 s vs 380.8 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorAddNoteHeader | Markor | Pass | Pass | 69.2 s | 224.2 s | 3.2× faster | Markor69.2 s vs 224.2 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorChangeNoteContent | Markor | Pass | Pass | 54.2 s | 217.5 s | 4.0× faster | Markor54.2 s vs 217.5 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorCreateFolder | Markor | Pass | Pass | 18.2 s | 157.9 s | 8.7× faster | Markor18.2 s vs 157.9 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorCreateNote | Markor | Pass | Pass | 30.2 s | 204.5 s | 6.8× faster | Markor30.2 s vs 204.5 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorCreateNoteAndSms | Markor | Pass | Pass | 57.2 s | 351.5 s | 6.1× faster | Markor57.2 s vs 351.5 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorCreateNoteFromClipboard | Markor | Pass | Pass | 36.2 s | 258.9 s | 7.2× faster | Markor36.2 s vs 258.9 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorDeleteAllNotes | Markor | Pass | Pass | 48.2 s | 198.6 s | 4.1× faster | Markor48.2 s vs 198.6 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorDeleteNewestNote | Markor | Pass | Pass | 21.2 s | 194.0 s | 9.2× faster | Markor21.2 s vs 194.0 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorDeleteNote | Markor | Pass | Pass | 21.2 s | 140.9 s | 6.6× faster | Markor21.2 s vs 140.9 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorEditNote | Markor | Pass | Pass | 27.3 s | 143.1 s | 5.2× faster | Markor27.3 s vs 143.1 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorMergeNotes | Markor | Pass | Pass | 72.2 s | 318.0 s | 4.4× faster | Markor72.2 s vs 318.0 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorMoveNote | Markor | Pass | Pass | 27.2 s | 275.9 s | 10.1× faster | Markor27.2 s vs 275.9 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorTranscribeReceipt | Markor | Pass | Pass | 45.2 s | 233.7 s | 5.2× faster | Markor45.2 s vs 233.7 sMobilerun’s grader: Pass · Google’s: Pass |
| MarkorTranscribeVideo | Markor | Pass | Pass | 354.2 s | 489.2 s | 1.4× faster | Markor354.2 s vs 489.2 sMobilerun’s grader: Pass · Google’s: Pass |
| NotesIsTodo | Joplin | Pass | Pass | 15.2 s | 85.9 s | 5.7× faster | Joplin15.2 s vs 85.9 sMobilerun’s grader: Pass · Google’s: Pass |
| NotesMeetingAttendeeCount | Joplin | Pass | Pass | 24.2 s | 147.0 s | 6.1× faster | Joplin24.2 s vs 147.0 sMobilerun’s grader: Pass · Google’s: Pass |
| NotesRecipeIngredientCount | Joplin | Pass | Pass | 21.2 s | 137.5 s | 6.5× faster | Joplin21.2 s vs 137.5 sMobilerun’s grader: Pass · Google’s: Pass |
| NotesTodoItemCount | Joplin | Pass | Pass | 30.2 s | 156.7 s | 5.2× faster | Joplin30.2 s vs 156.7 sMobilerun’s grader: Pass · Google’s: Pass |
| OpenAppTaskEval | Launcher | Pass | Pass | 24.2 s | 178.4 s | 7.4× faster | Launcher24.2 s vs 178.4 sMobilerun’s grader: Pass · Google’s: Pass |
| OsmAndFavorite | OsmAnd | Pass | Pass | 117.2 s | 166.8 s | 1.4× faster | OsmAnd117.2 s vs 166.8 sMobilerun’s grader: Pass · Google’s: Pass |
| OsmAndMarker | OsmAnd | Pass | Pass | 36.2 s | 212.6 s | 5.9× faster | OsmAnd36.2 s vs 212.6 sMobilerun’s grader: Pass · Google’s: Pass |
| OsmAndTrack | OsmAnd | Pass | Pass | 153.2 s | 887.7 s | 5.8× faster | OsmAnd153.2 s vs 887.7 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeAddMultipleRecipes | Broccoli | Pass | Pass | 186.2 s | 429.7 s | 2.3× faster | Broccoli186.2 s vs 429.7 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeAddMultipleRecipesFromImage | Broccoli | Pass | Pass | 222.3 s | 443.9 s | 2.0× faster | Broccoli222.3 s vs 443.9 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeAddMultipleRecipesFromMarkor | Broccoli | Pass | Pass | 198.4 s | 482.7 s | 2.4× faster | Broccoli198.4 s vs 482.7 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeAddMultipleRecipesFromMarkor2 | Broccoli | Pass | Pass | 249.2 s | 517.5 s | 2.1× faster | Broccoli249.2 s vs 517.5 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeAddSingleRecipe | Broccoli | Pass | Pass | 93.2 s | 244.8 s | 2.6× faster | Broccoli93.2 s vs 244.8 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteDuplicateRecipes | Broccoli | Pass | Pass | 51.2 s | 250.3 s | 4.9× faster | Broccoli51.2 s vs 250.3 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteDuplicateRecipes2 | Broccoli | Pass | Pass | 96.2 s | 327.1 s | 3.4× faster | Broccoli96.2 s vs 327.1 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteDuplicateRecipes3 | Broccoli | Pass | Pass | 240.2 s | 620.1 s | 2.6× faster | Broccoli240.2 s vs 620.1 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteMultipleRecipes | Broccoli | Pass | Pass | 39.2 s | 234.1 s | 6.0× faster | Broccoli39.2 s vs 234.1 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteMultipleRecipesWithConstraint | Broccoli | Pass | Pass | 282.3 s | 539.8 s | 1.9× faster | Broccoli282.3 s vs 539.8 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteMultipleRecipesWithNoise | Broccoli | Pass | Pass | 108.2 s | 474.7 s | 4.4× faster | Broccoli108.2 s vs 474.7 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteSingleRecipe | Broccoli | Pass | Pass | 18.2 s | 171.5 s | 9.4× faster | Broccoli18.2 s vs 171.5 sMobilerun’s grader: Pass · Google’s: Pass |
| RecipeDeleteSingleWithRecipeWithNoise | Broccoli | Pass | Pass | 48.2 s | 301.6 s | 6.3× faster | Broccoli48.2 s vs 301.6 sMobilerun’s grader: Pass · Google’s: Pass |
| RetroCreatePlaylist | Retro Music | Pass | Pass | 57.3 s | 663.2 s | 11.6× faster | Retro Music57.3 s vs 663.2 sMobilerun’s grader: Pass · Google’s: Pass |
| RetroPlayingQueue | Retro Music | Pass | Pass | 51.2 s | 768.0 s | 15.0× faster | Retro Music51.2 s vs 768.0 sMobilerun’s grader: Pass · Google’s: Pass |
| RetroPlaylistDuration | Retro Music | Pass | Pass | 240.2 s | 494.9 s | 2.1× faster | Retro Music240.2 s vs 494.9 sMobilerun’s grader: Pass · Google’s: Pass |
| RetroSavePlaylist | Retro Music | Pass | Pass | 84.4 s | 603.7 s | 7.2× faster | Retro Music84.4 s vs 603.7 sMobilerun’s grader: Pass · Google’s: Pass |
| SaveCopyOfReceiptTaskEval | Gallery | Pass | Pass | 51.2 s | 266.3 s | 5.2× faster | Gallery51.2 s vs 266.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAddOneEvent | Simple Calendar | Pass | Pass | 69.2 s | 420.8 s | 6.1× faster | Simple Calendar69.2 s vs 420.8 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAddOneEventInTwoWeeks | Simple Calendar | Pass | Pass | 69.2 s | 394.2 s | 5.7× faster | Simple Calendar69.2 s vs 394.2 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAddOneEventRelativeDay | Simple Calendar | Pass | Pass | 78.2 s | 435.5 s | 5.6× faster | Simple Calendar78.2 s vs 435.5 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAddOneEventTomorrow | Simple Calendar | Pass | Pass | 72.2 s | 328.1 s | 4.5× faster | Simple Calendar72.2 s vs 328.1 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAddRepeatingEvent | Simple Calendar | Pass | Pass | 78.2 s | 478.9 s | 6.1× faster | Simple Calendar78.2 s vs 478.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarAnyEventsOnDate | Simple Calendar | Pass | Pass | 21.2 s | 106.3 s | 5.0× faster | Simple Calendar21.2 s vs 106.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarDeleteEvents | Simple Calendar | Pass | Pass | 42.2 s | 261.4 s | 6.2× faster | Simple Calendar42.2 s vs 261.4 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarDeleteEventsOnRelativeDay | Simple Calendar | Pass | Pass | 33.2 s | 215.6 s | 6.5× faster | Simple Calendar33.2 s vs 215.6 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarDeleteOneEvent | Simple Calendar | Pass | Pass | 36.2 s | 266.2 s | 7.4× faster | Simple Calendar36.2 s vs 266.2 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarEventOnDateAtTime | Simple Calendar | Pass | Pass | 33.2 s | 122.3 s | 3.7× faster | Simple Calendar33.2 s vs 122.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarEventsInNextWeek | Simple Calendar | Pass | Pass | 93.1 s | 150.2 s | 1.6× faster | Simple Calendar93.1 s vs 150.2 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarEventsInTimeRange | Simple Calendar | Pass | Pass | 21.2 s | 110.1 s | 5.2× faster | Simple Calendar21.2 s vs 110.1 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarEventsOnDate | Simple Calendar | Pass | Pass | 24.2 s | 93.2 s | 3.9× faster | Simple Calendar24.2 s vs 93.2 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarFirstEventAfterStartTime | Simple Calendar | Pass | Pass | 42.2 s | 112.8 s | 2.7× faster | Simple Calendar42.2 s vs 112.8 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarLocationOfEvent | Simple Calendar | Pass | Pass | 18.2 s | 113.1 s | 6.2× faster | Simple Calendar18.2 s vs 113.1 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarNextEvent | Simple Calendar | Pass | Pass | 27.2 s | 116.5 s | 4.3× faster | Simple Calendar27.2 s vs 116.5 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleCalendarNextMeetingWithPerson | Simple Calendar | Pass | Pass | 81.2 s | 170.3 s | 2.1× faster | Simple Calendar81.2 s vs 170.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleDrawProCreateDrawing | Simple Draw Pro | Pass | Pass | 42.2 s | 275.3 s | 6.5× faster | Simple Draw Pro42.2 s vs 275.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsReply | Simple SMS | Pass | Pass | 21.2 s | 159.6 s | 7.5× faster | Simple SMS21.2 s vs 159.6 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsReplyMostRecent | Simple SMS | Pass | Pass | 27.2 s | 178.5 s | 6.6× faster | Simple SMS27.2 s vs 178.5 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsResend | Simple SMS | Pass | Pass | 24.2 s | 147.4 s | 6.1× faster | Simple SMS24.2 s vs 147.4 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsSend | Simple SMS | Pass | Pass | 21.2 s | 172.9 s | 8.2× faster | Simple SMS21.2 s vs 172.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsSendClipboardContent | Simple SMS | Pass | Pass | 24.7 s | 173.3 s | 7.0× faster | Simple SMS24.7 s vs 173.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SimpleSmsSendReceivedAddress | Simple SMS | Pass | Pass | 54.2 s | 198.1 s | 3.7× faster | Simple SMS54.2 s vs 198.1 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerActivitiesCountForWeek | OpenTracks | Pass | Pass | 351.3 s | 279.7 s | 1.3× slower | OpenTracks351.3 s vs 279.7 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerActivitiesOnDate | OpenTracks | Pass | Pass | 72.2 s | 399.9 s | 5.5× faster | OpenTracks72.2 s vs 399.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerActivityDuration | OpenTracks | Pass | Pass | 30.2 s | 246.9 s | 8.2× faster | OpenTracks30.2 s vs 246.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerLongestDistanceActivity | OpenTracks | Pass | Pass | 153.2 s | 239.2 s | 1.6× faster | OpenTracks153.2 s vs 239.2 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerTotalDistanceForCategoryOverInterval | OpenTracks | Pass | Pass | 144.2 s | 364.8 s | 2.5× faster | OpenTracks144.2 s vs 364.8 sMobilerun’s grader: Pass · Google’s: Pass |
| SportsTrackerTotalDurationForCategoryThisWeek | OpenTracks | Pass | Pass | 69.4 s | 217.0 s | 3.1× faster | OpenTracks69.4 s vs 217.0 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBluetoothTurnOff | Settings | Pass | Pass | 27.2 s | 125.1 s | 4.6× faster | Settings27.2 s vs 125.1 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBluetoothTurnOffVerify | Settings | Pass | Pass | 15.2 s | 136.9 s | 9.0× faster | Settings15.2 s vs 136.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBluetoothTurnOn | Settings | Pass | Pass | 18.2 s | 121.9 s | 6.7× faster | Settings18.2 s vs 121.9 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBluetoothTurnOnVerify | Settings | Pass | Pass | 24.2 s | 108.0 s | 4.5× faster | Settings24.2 s vs 108.0 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBrightnessMax | Settings | Pass | Pass | 18.2 s | 132.0 s | 7.3× faster | Settings18.2 s vs 132.0 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBrightnessMaxVerify | Settings | Pass | Pass | 27.2 s | 125.6 s | 4.6× faster | Settings27.2 s vs 125.6 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBrightnessMin | Settings | Pass | Pass | 33.2 s | 129.7 s | 3.9× faster | Settings33.2 s vs 129.7 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemBrightnessMinVerify | Settings | Pass | Pass | 18.2 s | 117.4 s | 6.5× faster | Settings18.2 s vs 117.4 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemCopyToClipboard | Settings | Pass | Pass | 54.8 s | 221.3 s | 4.0× faster | Settings54.8 s vs 221.3 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemWifiTurnOff | Settings | Pass | Pass | 24.2 s | 155.7 s | 6.4× faster | Settings24.2 s vs 155.7 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemWifiTurnOffVerify | Settings | Pass | Pass | 30.2 s | 93.7 s | 3.1× faster | Settings30.2 s vs 93.7 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemWifiTurnOn | Settings | Pass | Pass | 15.2 s | 110.6 s | 7.3× faster | Settings15.2 s vs 110.6 sMobilerun’s grader: Pass · Google’s: Pass |
| SystemWifiTurnOnVerify | Settings | Pass | Pass | 21.2 s | 97.1 s | 4.6× faster | Settings21.2 s vs 97.1 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksCompletedTasksForDate | Tasks | Pass | Pass | 117.3 s | 244.0 s | 2.1× faster | Tasks117.3 s vs 244.0 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksDueNextWeek | Tasks | Pass | Pass | 180.2 s | 154.4 s | 1.2× slower | Tasks180.2 s vs 154.4 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksDueOnDate | Tasks | Pass | Pass | 171.3 s | 139.4 s | 1.2× slower | Tasks171.3 s vs 139.4 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksHighPriorityTasks | Tasks | Pass | Pass | 273.3 s | 193.5 s | 1.4× slower | Tasks273.3 s vs 193.5 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksHighPriorityTasksDueOnDate | Tasks | Pass | Pass | 81.2 s | 133.7 s | 1.6× faster | Tasks81.2 s vs 133.7 sMobilerun’s grader: Pass · Google’s: Pass |
| TasksIncompleteTasksOnDate | Tasks | Pass | Pass | 219.2 s | 126.2 s | 1.7× slower | Tasks219.2 s vs 126.2 sMobilerun’s grader: Pass · Google’s: Pass |
| TurnOffWifiAndTurnOnBluetooth | Settings | Pass | Pass | 54.2 s | 164.8 s | 3.0× faster | Settings54.2 s vs 164.8 sMobilerun’s grader: Pass · Google’s: Pass |
| TurnOnWifiAndOpenApp | Settings | Pass | Pass | 51.2 s | 134.1 s | 2.6× faster | Settings51.2 s vs 134.1 sMobilerun’s grader: Pass · Google’s: Pass |
| VlcCreatePlaylist | VLC | Pass | Pass | 75.2 s | 331.1 s | 4.4× faster | VLC75.2 s vs 331.1 sMobilerun’s grader: Pass · Google’s: Pass |
| VlcCreateTwoPlaylists | VLC | Pass | Pass | 114.2 s | 420.5 s | 3.7× faster | VLC114.2 s vs 420.5 sMobilerun’s grader: Pass · Google’s: Pass |
Download data
¹ Google’s original grader failed two tasks Lusor completed: it looks for the recording name typed in full (….m4a.m4a), and for the expense notes without the “Reimbursable.” marker. Mobilerun’s fork of the grader accepts Lusor’s reading on both.
⁶ In BrowserMultiply the agent read the page’s code to find the fifth number. Its task page explains how.
Data schema: one row per task, fields task, app, goal, mobilerun_grader_pass, google_grader_pass, lusor_time_s, mobilerun_published_time_s, speed_ratio, lusor_cost_usd, lusor_tool_calls, mobilerun_published_actions, mobilerun_est_cost_usd, disclosure. Times are seconds; costs are US dollars; Mobilerun’s cost is our estimate; speed_ratio is Lusor’s time ÷ Mobilerun’s published time.