B-MoCA
Agents use Android apps such as Instagram on phones with different languages, font sizes, and icon positions. Task-specific checks decide whether each attempt succeeded.
MobileJudgeBench ran four agents on 35 B-MoCA tasks and released 123 trajectories. B-MoCA lists 131 tasks and ten test device configurations.
- Made by
- KAIST and Yonsei University
- Released
- April 2024
- Kind
- Phones
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Agentic
- Environment
- Phone apps
- Items from
- Written by experts, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Computer use, Agents, Many languages
- Strongest model tested
- GPT-4o May 2024 #162 on the capability index
- Last model added
- May 2024
- Scores refreshed
- November 20th, 2026
GPT-4o leads with 47.7% among models released by May 2024
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in May 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4o May 2024, Zero-shot 47.7%
- 2
Llama 3-70B Zero-shot 29.9%
- 3
Gemini 1.5 Pro May 2024, Zero-shot 29.5%
Source: The B-MoCA paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o May 2024 | 47.7% | Zero-shot, LLM Agent | May 2024 | Official leaderboard |
| 2 | | 29.9% | Zero-shot, LLM Agent | Apr 2024 | Official leaderboard |
| 3 | | 29.5% | Zero-shot, LLM Agent | May 2024 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s paper: Test Env 100, Test Env 101 and Test Env 105. Each ranks models on one part of the test. GPT-4o leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Test Env 100
3 models we track have a score here.
- 1 GPT-4o May 2024 53.7%
- 2
Llama 3-70B 37.4%
- 3
Gemini 1.5 Pro May 2024 36.1%
Test Env 101
3 models we track have a score here.
- 1 GPT-4o May 2024 47.1%
- 2
Llama 3-70B 28.2%
- 3
Gemini 1.5 Pro May 2024 27%
Test Env 105
3 models we track have a score here.
- 1 GPT-4o May 2024 42.2%
- 2
Gemini 1.5 Pro May 2024 ↑1 25.4%
- 3
Llama 3-70B ↓1 24.2%
2 models have held number one in the benchmark’s paper since its release in April 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The B-MoCA paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official B-MoCA leaderboard
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
- 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in May 2024, for Gemini 1.5 Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (3 entries).
- Note Models scored Only 3 models we track.
- Warning Newest score The newest came 2 years ago, in May 2024, for Gemini 1.5 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4o (#162).
- Pass Headroom The best is 47.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track 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.