Benchmark Almanac

OmniACT

UGround-V1-7B + GPT-4o 34.0 tops its leaderboard
Not in model cards

Models generate executable scripts from a screenshot and a user request. The evaluation compares the actions needed to complete desktop and web tasks.

The authors report human and model baselines.

Made by
OmniACT team and Writer
Released
February 2024
Kind
Desktop apps
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Screens → Code
Interaction
Single turn
Environment
Desktop apps, Browser
Refresh
One fixed set
Run by
Anyone
In views
Computer use
5
Entries on SOTA2’s leaderboard, 0 models we track

UGround-V1-7B + GPT-4o tops the leaderboard with 34.0

Best score per entry from SOTA2’s leaderboard, read on November 20th, 2026. 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.

  1. 1 UGround-V1-7B + GPT-4o Inputs=Image (SeeAct-V), Planner=GPT-4o 34.0
  2. 2 UGround-V1-2B + GPT-4o Inputs=Image (SeeAct-V), Planner=GPT-4o 32.9
  3. 3 UGround + GPT-4o Inputs=Image (SeeAct-V), Planner=GPT-4o 32.8
  4. 4 SeeClick + GPT-4o Inputs=Image (SeeAct-V), Planner=GPT-4o 29.6
  5. 5 GPT-4 (snapshot unspecified) Image + Text 17.0

Source: SOTA2’s leaderboard

#EntryScoreSettingDateSource
1 UGround-V1-7B + GPT-4o 34.0 Inputs=Image (SeeAct-V), Planner=GPT-4o, SeeAct-V Official leaderboard
2 UGround-V1-2B + GPT-4o 32.9 Inputs=Image (SeeAct-V), Planner=GPT-4o, SeeAct-V Official leaderboard
3 UGround + GPT-4o 32.8 Inputs=Image (SeeAct-V), Planner=GPT-4o, SeeAct-V Official leaderboard
4 SeeClick + GPT-4o 29.6 Inputs=Image (SeeAct-V), Planner=GPT-4o, SeeAct-V Official leaderboard
5 GPT-4 (snapshot unspecified) 17.0 Image + Text, DetACT Official 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

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 official leaderboard (5 entries).
  • Pass Models scored 5 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on SOTA2: 5 entries at the last read, none a model we track.
  • 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