Browse all Qwen text models
Provider logo

Qwen3.7 Max

qwen/qwen3.7-max
Provider logo

Qwen3.7 Max

qwen/qwen3.7-max

Qwen3.7 Max is Alibaba's latest flagship Qwen model for agentic coding, office automation, and long-running tool workflows in non-thinking mode.

Added May 21, 2026

Context Window

1.0M

Max Output

65.5K

Avg output tokens (7d)

1.6K tokens

84%

Input Price (Auto)

$1.47/1M

Output Price (Auto)

$4.42/1M

Cache Read (Auto)

$0.30/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

29.9

Better than 85% of models compared

Coding Index

66.0

Better than 77% of models compared

Agentic Index

23.9

Better than 64% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

23.0%

Better than 48% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

918 Elo

Better than 48% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1190 Elo

Better than 63% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

8.6%

Better than 40% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

79.0%

Better than 86% of models compared

Reasoning

HLE

Humanity's Last Exam

40.5%

Better than 91% of models compared

IFBench

Instruction-following benchmark

80.5%

Better than 98% of models compared

CritPt

Research-level physics reasoning

13.4%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

1.5%

Better than 50% of models compared

SciCode

Python programming for scientific computing

49.5%

Better than 55% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

31.1%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

25.6%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

92.3%

Better than 94% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

50.8%

Better than 95% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

94.7%

Better than 93% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

79.0%

Better than 86% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

34.5%

Last updated Sep 11, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Qwen3.7 Max with similar models from the same provider or model family.