Atlas
Benchmarks
326 sources · 1,256 models × 2,956 benchmarks · 154,484 scoresCua Driver Bench v2 (Windows, foreground)
Cua's Cua Driver Bench v2 on Windows 11 with the desktop to the agent: ten desktop tasks (three multi-app workflows, three precision interactions and four interruptions) done only through a computer-use driver's tools, with no shell or file access. A trial passes when the task's checker confirms the apps' final state and no route out of the GUI was used; each task runs five seeded trials and the rate is passes over trials.
Models
3
Top score
74.0
Leader
Claude Opus 5.5
Updated
—
Resolution
—
Saturation
—
No signal or difficulty estimate. Held out of the fit by design.
| # | Model | Setting | Score | Source |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | — · Cua Driver Bench on AgentEnv; Claude Code 2.1.280 with no --effort passed and its built-in tools limited to Skill and Read; trycua's cua-driver MCP tools alone; 45 turns and 360 seconds per trial | 74.0 | |
| 2 | Claude Haiku 5.5 | — · Cua Driver Bench on AgentEnv; Claude Code 2.1.280 with no --effort passed and its built-in tools limited to Skill and Read; trycua's cua-driver MCP tools alone; 45 turns and 360 seconds per trial | 70.0 | |
| 3 | Claude Sonnet 5.5 | — · Cua Driver Bench on AgentEnv; Claude Code 2.1.280 with no --effort passed and its built-in tools limited to Skill and Read; trycua's cua-driver MCP tools alone; 45 turns and 360 seconds per trial | 70.0 |
