Qwen4-Max1,750 Elo
Qwen4 launch snapshotLaunch comparison; effort and full harness unspecified.
Qwen Team ↗Web development preference ratings. Published Qwen4-Max launch results.
| Model / creator | Version | Reported score |
|---|---|---|
| Qwen4 launch snapshot | 1,750 Elo |
Launch comparison; effort and full harness unspecified.
Qwen Team ↗Legal agent work; metric not equated with Harvey LAB-AA all-pass.
RoboDojo SimTests controlling a simulated robot from visual information, helping you assess progress toward automating physical tasks.
SWE-bench VerifiedTests whether an agent can fix real GitHub issues, helping you choose a model for bug fixes and maintenance so you can focus on reviewing changes and serving clients.