Home/Models/Qwen3.7 Max
Alibaba Qwen logo

Qwen3.7 Max

by Alibaba Qwen · Released May 2026

Open Source1M Context
79.8
avg score
Rank #22
Compare
Better than 92% of all models
Context
1.0M tokens (~500 books)
Input $/1M
$1.25
Output $/1M
$3.75
Type
text
License
Open Source
Benchmarks
18 tested
Data updated today
About

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

Tested on 18 benchmarks with 68.1% average. Top scores: OTIS Mock AIME 2024-2025 (95.0%), GPQA diamond (88.8%), LiveBench — Mathematics (85.3%).

Looking for similar performance at lower cost?
MiniMax M3 scores 79.7 (100% as good) at $0.30/1M input · 76% cheaper
Capabilities
coding
62.9
#40 globally
reasoning
73.2
#29 globally
math
69.7
#40 globally
knowledge
60.9
#55 globally
language
76.9
#59 globally
speed
79.2
#13 globally
Benchmark Scores
Compare All
Tested on 18 benchmarks · Ranked across 6 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

74.2
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

51.7
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

83.3
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

71.8
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

64.5
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

95.0
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

85.3
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
qwen3-7-max
Specifications
  • Typetext
  • Context1.0M tokens (~500 books)
  • ReleasedMay 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.006
Available On
Alibaba Qwen logoAlibaba Qwen$1.25
Share & Export
Tweet
Qwen3.7 Max is an open-source text AI model by Alibaba Qwen, released in May 2026. It has an average benchmark score of 79.8. Context window: 1M tokens.