Qwen

Qwen3.7 Max

by Qwentext->text1 endpoint
Neura Intelligence Index
77.5/ 100
Rank
#45
Confidence
medium
Benchmarks
7(18% coverage)

Overview

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,...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
1M tokens
Max Output
131.1K tokens
Tokenizer
Qwen
Uptime (24h)
10000.0%
Country
🇨🇳CN
Release Date
May 19, 20264mo

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
90.3
verified

coding

BenchmarkScoreSource
SWE-bench Verified
80.4
verified
SWE-Bench Pro
60.6
verified
SciCode
53.5
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
92.4
verified
Humanity's Last Exam
41.4
verified

agent

BenchmarkScoreSource
MCP Atlas
76.4
verified

Performance Over Time

Pricing

Per 1M tokens
Input$1.48
Output$4.42
Cache read$0.29
Cache write$1.84
Added
May 21, 2026
Last synced 9/17/2026