Benchmark Almanac

Mobile-Eval-E

Not in model cards

Agents complete 25 smartphone tasks across 15 apps. Human reviewers score the share of task requirements each agent meets.

Agent-SAMA independently completed 21 of 25 tasks on a Pixel 7 Pro. That success rate uses a different metric from the original satisfaction score.

Released
January 2025
Kind
Phones
Level
Everyday
Scored
Graded by people
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Screens → Actions
Interaction
Agentic
Refresh
One fixed set
Run by
Anyone
Based on
Mobile-Eval
9
Entries in its paper, 0 models we track

Mobile-Agent-E + Evo + GPT-4o tops the leaderboard with 86.9% No scores yet

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Mobile-Agent-E + Evo + GPT-4o, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

  1. 1 Mobile-Agent-E + Evo + GPT-4o Nov 2024 86.9%
  2. 2 Mobile-Agent-E + Evo + Claude 3.5 Sonnet (October 2024) 83%
  3. 3 Mobile-Agent-E + Claude 3.5 Sonnet (October 2024) 75.5%
  4. 4 Mobile-Agent-E + GPT-4o Nov 2024 75.1%
  5. 5 gemini-1.5-pro-latest (Dec 2024) 71.2%
  6. 6 Mobile-Agent-v2 + Claude 3.5 Sonnet (October 2024) 70.9%
  7. 7 Mobile-Agent-v2 + GPT-4o Nov 2024 53%
  8. 8 Mobile-Agent-v1 + GPT-4o Nov 2024 45.5%
  9. 9 AppAgent + GPT-4o Nov 2024 25.2%

Source: The Mobile-Eval-E paper

#EntryScoreSettingDateSource
1 Mobile-Agent-E + Evo + GPT-4o Nov 2024 86.9% Nov 2024 Official leaderboard
2 Mobile-Agent-E + Evo + Claude 3.5 Sonnet (October 2024) 83% Oct 2024 Official leaderboard
3 Mobile-Agent-E + Claude 3.5 Sonnet (October 2024) 75.5% Oct 2024 Official leaderboard
4 Mobile-Agent-E + GPT-4o Nov 2024 75.1% Nov 2024 Official leaderboard
5 gemini-1.5-pro-latest (Dec 2024) 71.2% Mobile-Agent-E + Evo Official leaderboard
6 Mobile-Agent-v2 + Claude 3.5 Sonnet (October 2024) 70.9% Oct 2024 Official leaderboard
7 Mobile-Agent-v2 + GPT-4o Nov 2024 53% Nov 2024 Official leaderboard
8 Mobile-Agent-v1 + GPT-4o Nov 2024 45.5% Nov 2024 Official leaderboard
9 AppAgent + GPT-4o Nov 2024 25.2% Nov 2024 Official leaderboard
#ModelScoreSettingDateSource

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Computer and browser use

All 119 in Computer and browser use
  • BrowseComp In use Hard-to-find facts that need persistent web browsing. Short verifiable answers graded for exact correctness. Claude Fable 5 93.3%
  • ScreenSpot-Pro In use GUI grounding on high-resolution professional-software screenshots. The model must locate the target UI element. GPT-6 Astra 92.7%
  • AndroidWorld In use Agents complete 116 tasks across 20 real Android apps in an emulator. Each task checks the device's system state to judge success. GPT-6 Astra 100%
  • OSWorld 2.1 In use Agents complete 108 long-horizon workflows across 31 self-hosted websites and desktop apps, averaging 318 tool calls. Scored by binary completion and checkpoint partial credit. Claude Opus 5 44.3%
  • WebArena-Verified In use Agents complete 812 audited WebArena tasks on self-hosted websites. Deterministic evaluators check the agent's answer and captured network traces. Muse Spark 1.1 69%
  • OSWorld 2.1 (offline subset) In use Agents complete the 82 OSWorld 2.1 tasks on the official offline list, with no internet access. Scored by checkpoint partial credit and strict pass rate. Claude Fable 5.2 89.3%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 9 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 8 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check