Qwen3 Max Thinking (Preview)
AlibabaQwen
Release Date
2025-11-03
Parameters
—
Context Length
262K
Modalities
text
Capability Radar
44
general
36
coding
82
reasoning
51
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 161 | 49.0 | AA |
| General Ranking | 97 | 67.0 | AA |
| Math Reasoning | 74 | 83.0 | AA |
| Science | 131 | 57.0 | AA |
Benchmark Scores (LLM Stats)
No benchmark data available
AA Evaluation Indices
Math Index82.3
Intelligence Index32.5
Coding Index24.5
Tau20.8
Mmlu Pro0.8
Aime 250.8
Gpqa0.8
Lcr0.6
Ifbench0.5
Livecodebench0.5
Scicode0.4
Terminalbench Hard0.2
Hle0.1
LLM Stats Category Scores
No category score data available
Pricing
Input Price$1.2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$2.4 / 1M tokens
Speed
Tokens/sec45.9 tokens/s
Time to First Token1.70s
Time to Answer45.25s
Available Providers
(LS internal units)No provider data available
External Sources
No external links available