Provider logo

Qwen3.7 Plus Thinking

qwen3.7-plus:thinking
Provider logo

Qwen3.7 Plus Thinking

qwen3.7-plus:thinking

Qwen3.7 Plus with thinking mode enabled for deeper multimodal reasoning, coding, tool use, screen reading, and productivity workflows.

Added Jun 1, 2026

Context Window

983.6K

Max Output

65.5K

Avg output tokens (7d)

2.2K tokens

93%

Input Price (Auto)

$0.40/1M

Output Price (Auto)

$1.60/1M

Cache Read (Auto)

$0.080/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

25.8

Better than 80% of models compared

Coding Index

55.9

Better than 66% of models compared

Agentic Index

19.7

Better than 56% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

17.4%

Better than 43% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

913 Elo

Better than 48% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

886 Elo

Better than 42% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

12.2%

Better than 54% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

73.0%

Better than 73% of models compared

Reasoning

HLE

Humanity's Last Exam

35.6%

Better than 87% of models compared

IFBench

Instruction-following benchmark

78.0%

Better than 97% of models compared

CritPt

Research-level physics reasoning

9.1%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

1.0%

Better than 46% of models compared

SciCode

Python programming for scientific computing

46.1%

Better than 46% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

22.5%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

27.7%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

90.0%

Better than 89% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

47.0%

Better than 94% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

93.0%

Better than 89% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

73.0%

Better than 73% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

19.3%

Last updated Sep 10, 2026

Artificial Analysis

Providers

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

Loading provider options…

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