Benchmark Almanac

ScreenSuite

Not in model cards

Models use screenshots to locate controls, select actions and complete computer tasks. The suite measures perception, single actions and complete interactions.

The official repository had 151 GitHub stars. Hugging Face published model comparisons with the release.

Made by
Hugging Face
Released
June 2025
Kind
Desktop apps
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Screens, Text → Actions
Interaction
Agentic
Environment
Desktop apps
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Computer use, Agents
Last model added
March 2025
Scores refreshed
November 21st, 2026
3
Entries in its paper, 2 models we track

Qwen2.5-VL-72B leads with 56% Qwen2.5-VL-72B leads with 56%

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The source reports no overall score, so this is the plain mean of its 12 benchmark scores. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 Qwen2.5-VL-72B 56%
  2. 2 Qwen2.5-VL-32B 51.1%
  3. 3 GPT-4o (snapshot unspecified) 32.4%

Source: The ScreenSuite paper

Source: The ScreenSuite paper

#EntryScoreSettingDateSource
1 Qwen2.5-VL-72B 56% Jan 2025 Official leaderboard
2 Qwen2.5-VL-32B 51.1% Mar 2025 Official leaderboard
3 GPT-4o (snapshot unspecified) 32.4% Official leaderboard
#ModelScoreSettingDateSource
1 Qwen2.5-VL-72B 56% Jan 2025 Official leaderboard
2 Qwen2.5-VL-32B 51.1% Mar 2025 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Qwen2.5-VL-72B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) Qwen2.5-VL-72B

Source: Official ScreenSuite 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 20 months ago, in March 2025, for Qwen2.5-VL-32B. 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 2 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for Qwen2.5-VL-32B.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 56%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 2 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 21st, 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