Qwen4-Max68.5%
Qwen4 launch / updated dataset and evaluatorLaunch comparison; effort and full harness unspecified. Dataset commit d43a66575635da0d3f6cb9a20976dc1a60f3ffc9; evaluator 660b33a86ed032559df0b2fdc1ad38cf7ceb83f3.
Qwen Team ↗Professional job tasks. Published Qwen4-Max launch results.
| Model / creator | Version | Reported score |
|---|---|---|
| Qwen4 launch / updated dataset and evaluator | 68.5% |
Launch comparison; effort and full harness unspecified. Dataset commit d43a66575635da0d3f6cb9a20976dc1a60f3ffc9; evaluator 660b33a86ed032559df0b2fdc1ad38cf7ceb83f3.
Qwen Team ↗Tests difficult visual reasoning, helping you assess which model can interpret complex visual material before using it in client analysis.
Gaia2Tests whether an assistant can coordinate work across email, calendars, shopping and other apps, helping you assess how much routine planning and execution you could hand off.
LiveBench: AgenticTests extended tasks that require an agent to keep working toward a goal, helping you assess which model could handle longer assignments with less step-by-step direction.