Context
262K tokens (~131 books)
Input $/1M
$0.78
Output $/1M
$3.90
Type
text
License
Open Source
Benchmarks
3 tested
Data updated today
About
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
Tested on 3 benchmarks with 0.0% average. Top scores: Artificial Analysis — Agentic Index (50.1%), Artificial Analysis — Quality Index (39.9%), Artificial Analysis — Coding Index (30.5%).
Capabilities
speed
66.9
#25 globally
Benchmark Scores
Compare AllTested on 3 benchmarks · Ranked across 1 categories
Score Distribution (all 233 models)
0255075100
speedCompare speed →
Artificial Analysis — Agentic Index
50.1—Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.
Artificial Analysis — Quality Index
39.9—Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.
Artificial Analysis — Coding Index
30.5—Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
qwen3-max-thinking
Specifications
- Typetext
- Context262K tokens (~131 books)
- ReleasedFeb 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.005
Available On
Categories
Share & Export
Frequently Asked Questions
Qwen3 Max Thinking is an open-source text AI model by Alibaba Qwen, released in February 2026. Context window: 262K tokens.