New: Qwen4-Max eval report is here.Read the report ↗

Best models for professional job tasks

JobBench

Professional job tasks. Published Qwen4-Max launch results.

Updated: Data as of:
Limited reportingNot saturated
Official benchmark
JobBench results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creatorVersionReported score
Qwen4-MaxQwen · ProprietaryQwen4 launch / updated dataset and evaluator68.5%
View all 1 published reports
Qwen4 launch / updated dataset and evaluator

Launch comparison; effort and full harness unspecified. Dataset commit d43a66575635da0d3f6cb9a20976dc1a60f3ffc9; evaluator 660b33a86ed032559df0b2fdc1ad38cf7ceb83f3.

Qwen Team ↗