Skip to content

Alibaba

Qwen3-235B-A22B-Thinking-2507

Announced
Access
Public

Benchmark scores

TestScoreBest on the trackerHow it was measured
GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated80%Gemini 4 Argon 96%Independentdefault settings (Qwen3-235B-A22B-Thinking-2507)Run 11 Dec 2025
OTIS Mock AIMEcompetition mathsSaturated87%GPT-5.5 100%Independentdefault settings (Qwen3-235B-A22B-Thinking-2507)Run 10 Dec 2025

Compare every model on the same tests →

Sources