Qwen3 Max Thinking (Preview)
Released · 13 days after Qwen3 VL 32B
Benchmarks
Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.
Global rank#189 of 511 LLMs
TierEfficient
Intelligence Index (previous version)16.3
Coding
LiveCodeBench
54%
Agentic & knowledge work
Terminal-Bench Hard
17%
τ²-Bench Telecom
84%
Science & reasoning
Humanity's Last Exam
13%
GPQA Diamond
78%
Long-context reasoning
62%
Knowledge
MMLU-Pro
82%
Math & instruction following
AIME 2025
82%
IFBench
54%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Qwen3 Max Thinking (Preview) isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →