Benchmarks
326 sources · 1,256 models × 2,956 benchmarks · 154,484 scoresCua's Cua Driver Bench v2 on Windows 11 while a simulated user keeps typing in a window in front: eight of its ten desktop tasks, 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; each task runs five seeded trials and the rate is passes over trials.
No signal or difficulty estimate. Held out of the fit by design.
| # | Model | Setting | Score | Source |
|---|---|---|---|---|
| 1 | 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 | 27.5 | |
| 2 | 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 | 25.0 | |
| 3 | 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 | 20.0 |