Qwen4-Max7.5 points
Qwen4 launch snapshotLaunch comparison; effort and full harness unspecified.
Qwen Team ↗Real-world agent tasks. Published Qwen4-Max launch results.
| Model / creator | Version | Reported score |
|---|---|---|
| Qwen4 launch snapshot | 7.5 points |
Launch comparison; effort and full harness unspecified.
Qwen Team ↗Tests extracting text, tables and formulas from documents, helping you choose a model for turning client files into usable data with less manual copying.
OSWorldComputer interaction on OSWorld’s 82-task offline subset, scored with partial credit.
Humanity’s Last ExamTests whether a model can work through difficult expert-level questions, helping you choose an assistant for demanding research and technical analysis.