Atlas

Benchmarks

FrontierCUA v1 pass@1

FrontierCUA v1, Collinear AI's private computer-use benchmark of 40 held-out connected workflows across running clones of enterprise applications such as HubSpot, Zendesk, Slack and Google Sheets; agents work only from the screen, a screenshot and one mouse or keyboard action per step, and an AI judge scores each workflow's weighted rubric of yes-or-no checks from the recorded final application state. Each model has one graded attempt per workflow; an attempt passes at a grade of at least 0.95, and pass@1 is the share of workflows passed. A new task cohort, kept separate from the 15-workflow v0 snapshot.

Models
25
Top score
42.5
Leader
Gemini 4 Carbon
Updated
Nov 20, 2026
Resolution
~3 mo
Sharp
Saturation
~May 2028
Projected
Signal
67thpercentile
141 benchmarks from 0.8 to 2.9196 benchmarks from 2.9 to 5.0131 benchmarks from 5.0 to 7.1105 benchmarks from 7.1 to 9.282 benchmarks from 9.2 to 11.365 benchmarks from 11.3 to 13.327 benchmarks from 13.3 to 15.421 benchmarks from 15.4 to 17.58 benchmarks from 17.5 to 19.68 benchmarks from 19.6 to 21.76 benchmarks from 21.7 to 23.84 benchmarks from 23.8 to 25.95 benchmarks from 25.9 to 28.03 benchmarks from 28.0 to 30.12 benchmarks from 30.1 to 32.14 benchmarks from 32.1 to 34.21 benchmark from 34.2 to 36.33 benchmarks from 36.3 to 38.41 benchmark from 38.4 to 40.52 benchmarks from 40.5 to 42.61 benchmark from 42.6 to 44.71 benchmark from 44.7 to 46.81 benchmark from 48.9 to 50.9

267th strongest of 818

Signal-to-noise +8.69

Difficulty
94thpercentile
1 benchmark from 5.8 to 14.71 benchmark from 23.5 to 32.42 benchmarks from 32.4 to 41.21 benchmark from 41.2 to 50.12 benchmarks from 50.1 to 58.99 benchmarks from 58.9 to 67.88 benchmarks from 67.8 to 76.718 benchmarks from 76.7 to 85.523 benchmarks from 85.5 to 94.441 benchmarks from 94.4 to 103.232 benchmarks from 103.2 to 112.141 benchmarks from 112.1 to 121.049 benchmarks from 121.0 to 129.875 benchmarks from 129.8 to 138.760 benchmarks from 138.7 to 147.5122 benchmarks from 147.5 to 156.4135 benchmarks from 156.4 to 165.3124 benchmarks from 165.3 to 174.139 benchmarks from 174.1 to 183.021 benchmarks from 183.0 to 191.88 benchmarks from 191.8 to 200.72 benchmarks from 200.7 to 209.54 benchmarks from 209.5 to 218.4

50th hardest of 818

Capability needed ≳ 179.5

Organizations
25 dated models · 5 frontier modelsClosed weightsOpen weights
Data: Collinear AIatlas.village.dev

FrontierCUA v1 pass@1 leaderboard

#ModelSettingScoreSource
1Gemini 4 Carbonhigh
42.5
2GPT-6.2 Astrahigh · Codex
32.5
3Claude Fable 5.2high
25.0
4GPT-6.1 Solhigh · Codex
25.0
5GPT-6.2 Solhigh · Codex
25.0
6GPT-6 Astrahigh · Codex
20.0
7Claude Opus 5high
17.5
8MiniMax M3.1 Flashmax
17.5
9Qwen4-Maxhigh · Qwen-Agent computer-use harness (OSWorld-V2 QwenAgent port) via OpenRouter
17.5
10Claude Fable 5.1high
15.0
11Claude Fable 5high
15.0
12Claude Opus 5.5high
12.5
13Sonnet 5high
12.5
14Kimi K3high
12.5
15MiMo-V2.6-Flashhigh
12.5
16Muse Wonderhigh
12.5
17GPT-5.6 Solhigh · Codex
7.5
18GPT-6.1 Terrahigh · Codex
7.5
19GPT-6 Solhigh · Codex
7.5
20Grok 4.7high
7.5
21Muse Emberhigh
7.5
22MiMo-V2.6-Prohigh
5.0
23GLM-5.3 Flashhigh · GLM-5.3-FlashX inference-speed tier via Alibaba Cloud
2.5
24Kimi K3.1 Prohigh
2.5
25Muse Spark 1.3high
0.0

Related benchmarks

Loading Atlas data…