Qwen3.7 Max

Creator

Alibaba

Released

2026-05-19

Intelligence

46.0

Artificial Analysis Index

Coding

66.0

Artificial Analysis Index

In $/1M

$2.50

input tokens

Out $/1M

$7.50

output tokens

Blended $/1M

$3.75

3:1 blended

Speed

202

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Proprietary

non-commercial

Weights

Closed

API only

Modalities

Text

Parameters

Qwen3.7 Max is Alibaba Cloud Qwen Team's proprietary flagship model for agent-driven workflows. It is designed for coding agents, office automation, MCP and multi-agent orchestration, and long-horizon autonomous execution, with a 1 million token context window and up to 65,536 output tokens. Qwen reports strong agentic coding results including 69.7 on Terminal-Bench 2.0-Terminus, 80.4 on SWE-bench Verified, 60.6 on SWE-Pro, and 78.3 on SWE-Multilingual, alongside 92.4 on GPQA Diamond and 97.1 on HMMT 2026 Feb.

Capability profile

Category strength across 20 domains, via LLM Stats.

legal
100finance
100agents
100reasoning
100general
100language
90multimodal
90productivity
90spatial reasoning
90structured output
90instruction following
90
physics
80healthcare
80frontend development
80code
70math
70biology
70chemistry
70economics
70tool calling
70vision
60
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
92
Humanity’s Last Exam
38
MMLU-Pro
SciCode
49
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
95
Terminal-Bench Hard
51
IFBench
81
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
Novita$1.25$3.75active
Together$2.50$7.50active
All providers

2 hosts · via LLM Stats

© 2026 NYSGPT2525 LLC