benchgap
Alibaba (Qwen) · model

Qwen3.8 Max (0902) benchmark scores

As of 2026-10-07, Qwen3.8 Max (0902) (Alibaba (Qwen)) has measured scores on 16 benchmarks.

BenchmarkScoreSource
Terminal-Bench 2.188.8%measured
Terminal-Bench 4.038.9%measured
Terminal-Bench Science 0.111.9%measured
GPQA Diamond92.8%measured
SciCode52.1%measured
CritPt17.7%measured
GDP.pdf22.8%measured
τ³-Bench Banking47.8%measured
MMMU-Pro83.0%measured
AA-AnalystAgent45.0%measured
Harvey LAB93.6%measured
Humanity's Last Exam43.1%measured
AutomationBench56.2%measured
EnterpriseOps-Gym47.6%measured
APEX-Agents42.4%measured
ITBench SRE40.3%measured