Benchmark Almanac

B-MoCA

GPT-4o May 2024 47.7% leads since May 2024
Not in model cards

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
In and out
Text, Screens → Actions
Interaction
Agentic
Environment
Phone apps
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-4o May 2024 #162 on the capability index
Last model added
May 2024
Scores refreshed
November 20th, 2026
3
Models scored in its paper

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:

  1. 1 GPT-4o May 2024, Zero-shot 47.7%
  2. 2 Llama 3-70B Zero-shot 29.9%
  3. 3 Gemini 1.5 Pro May 2024, Zero-shot 29.5%

Source: The B-MoCA paper

#ModelScoreSettingDateSource
1 GPT-4o May 2024 47.7% Zero-shot, LLM Agent May 2024 Official leaderboard
2 Llama 3-70B 29.9% Zero-shot, LLM Agent Apr 2024 Official leaderboard
3 Gemini 1.5 Pro May 2024 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. 1 GPT-4o May 2024 53.7%
  2. 2 Llama 3-70B 37.4%
  3. 3 Gemini 1.5 Pro May 2024 36.1%

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.

Meta OpenAI
Benchmark paper Not tested since May 2024
GPT-4o 47.7%

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.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4o Llama 3-70B 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4o Llama 3-70B

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

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

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.

How we check