Benchmark Almanac

CutVerse

Claude Opus 4.6 68.3% leads since May 2026
Not in model cards

Agents complete editing tasks in seven applications, including Premiere Pro, Photoshop, and DaVinci Resolve. Vision models grade progress against milestones in the recorded workflow.

The paper reports 186 tasks. The authors publish the Windows harness. The public tasks directory contains a Notepad example.

Released
May 2026
Kind
Desktop apps
Level
University
Scored
Graded by a model
Answers
Agent task
Measures
Capability
Subject
Arts
Language
English
In and out
Text, Screens → Actions
Interaction
Agentic
Refresh
One fixed set
Run by
Anyone
In views
Computer use, Agents
Strongest model tested
Claude Opus 4.6 #39 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
5
Entries in its paper, 4 models we track

Claude Opus 4.6 leads with 68.3% among models released by February 2026 Claude Opus 4.6 leads with 68.3% among models released by February 2026

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 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.

The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Opus 4.6 68.3%
  2. 2 Gemini 3 Flash 67.2%
  3. 3 EvoCUA-32B 51.6%
  4. 4 Qwen3-VL-32B-Thinking 48.4%
  5. 5 UI-TARS-1.5 44.1%

Source: The CutVerse paper

#EntryScoreSettingDateSource
1 Claude Opus 4.6 68.3% Feb 2026 Official leaderboard
2 Gemini 3 Flash 67.2% Dec 2025 Official leaderboard
3 EvoCUA-32B 51.6% Official leaderboard
4 Qwen3-VL-32B-Thinking 48.4% Oct 2025 Official leaderboard
5 UI-TARS-1.5 44.1% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.6 68.3% Feb 2026 Official leaderboard
2 Gemini 3 Flash 67.2% Dec 2025 Official leaderboard
3 Qwen3-VL-32B-Thinking 48.4% Oct 2025 Official leaderboard
4 UI-TARS-1.5 44.1% Apr 2025 Official leaderboard

Rankings by part

We read 16 parts from the benchmark’s paper in 2 groups: task success and execution accuracy by application. Each ranks models on one part of the test. Gemini 3 Flash leads 7 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Generative Workflow (GW)

4 models we track have a score here.

  1. 1 UI-TARS-1.5 ↑3 100%
  2. 2 Qwen3-VL-32B-Thinking ↑1 100%
  3. 3 Gemini 3 Flash ↓1 100%
  4. 4 Claude Opus 4.6 ↓3 100%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Benchmark paper Not tested since May 2026

Source: The CutVerse 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% 2025 2026 Near the ceiling (85%) Claude Opus 4.6 Qwen3-VL-32B-Thinking UI-TARS-1.5 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.6 Qwen3-VL-32B-Thinking

Source: Official CutVerse 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 10 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Claude Opus 4.6.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 4.6 (#39).
  • Pass Headroom The best is 68.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 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