Atlas

Benchmarks

Cua Driver Bench v2 (macOS, background)

Cua

Cua's Cua Driver Bench v2 on macOS 26 while a simulated user keeps typing in a window in front: eight of its ten desktop tasks (the two hover tasks run only in the foreground), done only through a computer-use driver's tools. A trial passes when the task's checker confirms the apps' final state, no route out of the GUI was used and none of eight disturbances reached the user (lost focus, a window raised over theirs, lost typing, pointer, clipboard, Space, a dialog or deactivation); each task runs five seeded trials and the rate is passes over trials.

Models
4
Top score
57.5
Leader
Claude Opus 5.5
Updated
—
Resolution
—
Saturation
—

No signal or difficulty estimate. Held out of the fit by design.

4 dated models · 1 frontier modelsClosed weightsOpen weights
Data: Scale AIatlas.village.dev
#ModelSettingScoreSource
1Claude 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
57.5
2Claude 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
57.5
3Claude 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
45.0
4GPT-6.1 Solmedium · Cua Driver Bench on AgentEnv; Codex CLI 0.147.0 with every built-in Codex tool off; trycua's cua-driver MCP tools alone, whose screenshots Codex doesn't pass to the model; stopped after 45 tool calls or 360 seconds per trial
40.0
Loading Atlas data…