ZMIME
Alibaba (Qwen) · Released May 21, 2026

Qwen3.7 Max

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks.

  • Proprietary
  • Reasoning
  • Tool calling
Capability
153.7ECI · #37 of 148
Input
$2.50per 1M tokens
Output
$7.50per 1M tokens
Context
1M66K max output
Pricing

What it costs

Input
$2.50per million tokens
Output
$7.50per million tokens
Cached input
$0.50per million tokens
Cache write
$3.13per million tokens
Blended (3:1)
$3.75pricier than 82% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$8.75
Team assistant25M input + 5M output tokens$100.00
Production app250M input + 50M output tokens$1,000

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

153.7Epoch Capabilities Index
#37 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (151.9–156.0); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions90.9%
  • FrontierMath Tiers 1–3Research-level mathematics64.6%
  • OTIS Mock AIME 2024–2025Competition mathematics95.6%
  • SWE-bench VerifiedFixing real GitHub issues77.3%
  • SimpleQA VerifiedShort factual questions55.8%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
May 21, 2026
Context window
1,000,000 tokens
Max output
65,536 tokens
Inputs
Text
Output
Text
Reasoning
Thinking budget
Tool calling
Yes
Structured output
No
Weights
Proprietary
API model ID
qwen3.7-maxon Alibaba
Availability
26 API providerslisted on models.dev

Alibaba model documentation

Lab-reported

What Alibaba (Qwen) claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
SWE-Bench Verified80.4 resolved—Source
SWE-Bench Pro60.6 resolve rate—Source
SWE-Bench Multilingual78.3 resolve rate—Source
Terminal-Bench v2.069.7 success rate—Source
GPQA Diamond92.4—Source
Humanity's Last Exam41.4—Source
SciCode53.5—Source
MCP Atlas76.4 success rate—Source
NL2Repo47.2—Source
Same lab

More from Alibaba (Qwen)

Questions

About Qwen3.7 Max

How much does Qwen3.7 Max cost?

Qwen3.7 Max costs $2.50 input / $7.50 output per million tokens (official Alibaba API price). Cached input is $0.50 per million tokens, and writing to the cache costs $3.13. At a 3:1 input-to-output mix that is $3.75 per million tokens, more expensive than 82% of the 360 priced models we track.

What is the context window of Qwen3.7 Max?

Qwen3.7 Max accepts up to 1,000,000 tokens per request and can write up to 65,536 tokens in one response.

How good is Qwen3.7 Max?

Epoch AI gives Qwen3.7 Max a Capabilities Index score of 153.7 (likely range 151.9–156.0), ranking it #37 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 90.9%, FrontierMath Tiers 1–3 64.6%, OTIS Mock AIME 2024–2025 95.6%, SWE-bench Verified 77.3%, SimpleQA Verified 55.8%.

Is Qwen3.7 Max open source?

No. Qwen3.7 Max is proprietary; you use it through Alibaba’s API or partner platforms.

What inputs does Qwen3.7 Max support?

Qwen3.7 Max accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Qwen3.7 Max released?

Alibaba (Qwen) released Qwen3.7 Max on May 21, 2026.

What are the best alternatives to Qwen3.7 Max?

The closest current models from other labs on capability, price and release date are Gemini 3.5 Flash (Google, ECI 154.5, $1.50 / $9.00), Grok 4.5 (xAI, ECI 154.0, $2.00 / $6.00), Claude Sonnet 5 (Anthropic, ECI 156.3, $2.00 / $10.00) and GPT-5.2 (OpenAI, ECI 153.5, $1.75 / $14.00).