Qwen3 Max Thinking
AlibabaQwenProprietary
Description
The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques
Release Date
2026-01-26
Parameters
1.0T
Context Length
262K
Modalities
text
Capability Radar
60
general
50
coding
70
reasoning
77
scienceest.
40
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 107 | 41.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
VITA-Bench
40.9%SR
MCP-Mark
33.5%SR
DeepPlanning
28.7%SR
Toolathlon
18.8%SR
Chat
IFEvalGoogle Research (2023)
93.4%SR
Multi-Challenge
63.3%SR
Code
SecCodeBench
57.5%SR
General
C-Eval
93.7%SR
MAXIFE
84.0%SR
NOVA-63
54.2%SR
Instruction Following
IFBench
70.9%SR
Knowledge
HLE-Verified
37.6%SR
Language
MMLU-Redux
92.8%SR
MMLU-Pro
85.7%SR
MMMLU
84.4%SR
WMT24++
77.6%SR
Long Context
LongBench v2
60.6%SR
Math
AIME 2026
93.3%SR
IMO-AnswerBench
83.9%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
87.4%SR
Global PIQA
86.0%SR
LiveCodeBench v6
85.9%SR
SWE-Bench Verified
75.3%SR
AA-LCR
68.7%SR
SuperGPQA
67.3%SR
SWE-bench Multilingual
66.7%SR
BrowseComp-zh
60.9%SR
BrowseCompOpenAI (2025)
53.9%SR
Humanity's Last Exam (with tools, text-only)
49.8%SR
Seal-0
46.9%SR
Humanity's Last Exam (no tools, text-only)
30.2%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)
22.5%SR
Search
WideSearch
57.9%SR
Tool Calling
BFCL-V4
67.7%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Language90
Biology90
Chat80
Instruction Following80
Legal80
Physics80
Structured Output80
Finance80
Frontend Development80
Healthcare80
Chemistry80
Math70
Economics70
Long Context60
Reasoning60
General60
Communication60
Search50
Code50
Knowledge40
Agents40
Tool Calling40
Pricing
Input Price$1.2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$2.4 / 1M tokens
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
2 providers
Cheapest: AlibabaMost Expensive: DeepInfra
ProviderInputOutput
1AlibabaPRIMARY
$1.2
$6
2DeepInfra
$1.2
$6
Compare pricing across different API providers for this model.