What is Qwen 3.7-Max?

Qwen 3.7-Max is a top-tier frontier AI model, developed by Alibaba and released in 2026-05. It is best known for real-world software engineering performance, scoring 80.4% on SWE-bench Verified.

Is Qwen 3.7-Max available as an open-weight model?

Qwen 3.7-Max is a proprietary closed-weight model. Its weights are not publicly available — access is through the Alibaba API only.

What benchmarks has Qwen 3.7-Max been evaluated on?

Qwen 3.7-Max has been evaluated on: SWE-bench Verified (80.4%), GPQA Diamond (92.4%), MMLU-Pro (89.6%), LiveCodeBench (91.6%), Terminal-Bench (69.7%), HLE (41.4%), AA Intelligence Index (56.6 pts). Scores tagged SR are self-reported by the provider; scores tagged 3P or AA have been independently verified by third parties.

Is Qwen 3.7-Max available in FlowHunt?

Yes — Qwen 3.7-Max is directly available in FlowHunt. You can use it to build AI agents, automated workflows, chatbots, and document processing pipelines without any additional setup.

How does Qwen 3.7-Max compare to other AI models?

You can compare Qwen 3.7-Max against all 24 models tracked on the FlowHunt AI Leaderboard using the sortable benchmark table. The Benchmark Rankings section on this page shows Qwen 3.7-Max's position on each benchmark it has been evaluated on.

Alibaba

Qwen 3.7-Max

FrontierAvailable in FlowHunt

Try in FlowHunt

Qwen 3.7-Max is a top-tier frontier AI model, developed by Alibaba and released in May 2026. It is a proprietary closed-weight model, available through the Alibaba API. The 1M-token context window is large enough to hold entire codebases, lengthy technical documents, or extended agentic sessions without truncation.

On the FlowHunt AI Leaderboard it is one of 24 tracked models, evaluated across 8 benchmarks. Standout scores: 89.6% on MMLU-Pro (#1 of 8); 91.6% on LiveCodeBench (#2 of 5); 41.4% on HLE (#2 of 6).

Qwen 3.7-Max was released on May 20, 2026 as the top model in Alibaba’s Qwen 3 generation, introducing what Alibaba called a ’thinking mode’ — an extended chain-of-thought reasoning capability that can be toggled per query. In thinking mode, the model runs an internal deliberation step before producing its final answer, improving performance substantially on multi-step reasoning tasks. At launch Qwen 3.7-Max scored 92.4% on GPQA Diamond (third globally), 91.6% on LiveCodeBench, and 60.6% on SWE-bench Pro — the highest open-API score on that benchmark. Combined with a 1M context window and competitive API pricing, it established itself as the primary Frontier-tier alternative for cost-conscious enterprise teams.

Note: GPQA Diamond leader (92.4%). SWE-Pro leader (60.6%). AA Index 56.6.

Try in FlowHunt

Released: May 2026
Context: 1M tokens
Weights: Closed
Tier: Frontier
Provider: Alibaba

Qwen 3.7-Max Benchmark Rankings

Rank among all 24 models tracked on this leaderboard. SR = self-reported · 3P / AA / C = independently verified.

Benchmark	Score	Rank	Source	What it measures
SWE-bench Verified	80.4%	7 of 13	SR	Real GitHub issue resolution (500 verified issues)
SWE-bench Pro	60.6%	4 of 9	SR	Multi-language, standardised scaffold
GPQA Diamond	92.4%	4 of 14	SR	Graduate-level Google-proof science Q&A
MMLU-Pro	89.6%	1 of 8	SR	Hard knowledge reasoning, 12K questions
LiveCodeBench	91.6%	2 of 5	SR	Competitive programming, continuously updated
Terminal-Bench	69.7%	3 of 8	SR	Agentic Linux terminal task completion
HLE	41.4%	2 of 6	SR	Humanity's Last Exam (50+ STEM disciplines)
AA Intelligence Index	56.6 pts	4 of 9	AA	Artificial Analysis composite score (independent)

Detailed Benchmark Scores

SWE-V SR

80.4%

Real GitHub issue resolution (500 verified issues)

SWE-Pro SR

60.6%

Multi-language, standardised scaffold

GPQA ◇ SR

92.4%

Graduate-level Google-proof science Q&A

MMLU-P SR

89.6%

Hard knowledge reasoning, 12K questions

LiveCode SR

91.6%

Competitive programming, continuously updated

Terminal SR

69.7%

Agentic Linux terminal task completion

HLE SR

41.4%

Humanity's Last Exam (50+ STEM disciplines)

AA Idx AA

56.6 pts

Artificial Analysis composite score (independent)

Qwen 3.7-Max vs. Frontier Peers

Head-to-head benchmark comparison with other Frontier-tier models. Higher is better for all metrics.

Benchmark	Qwen 3.7-Max	Claude Opus 4.8	Claude Opus 4.7
SWE-V	80.4%	88.6%	87.6%
SWE-Pro	60.6%	69.2%	64.3%
GPQA ◇	92.4%	93.6%	94.2%
MMLU-P	89.6%	—	—
LiveCode	91.6%	—	—
Terminal	69.7%	74.6%	66.1%
HLE	41.4%	—	—
AA Idx	56.6 pts	61.4 pts	57.3 pts

About Alibaba

Alibaba Founded 1999 · Hangzhou, China

Website →

Alibaba Group is one of China's largest and most diverse technology conglomerates, founded in 1999 by Jack Ma and headquartered in Hangzhou. Through its DAMO Academy and Tongyi Lab, Alibaba has become a major force in large language model development with the Qwen (Tongyi Qianwen) family. The Qwen 3.7 generation, released in mid-2026, marked Alibaba's transition from domestic deployments to international benchmark competitiveness, with Qwen 3.7-Max scoring 92.4% on GPQA Diamond and 91.6% on LiveCodeBench. Alibaba's AI strategy is defined by open-weight releases as a counterbalance to US API-only models, integration of generative AI across its cloud and e-commerce businesses, and heavy investment in AI infrastructure across its Alibaba Cloud division.

Use Cases

What to Use Qwen 3.7-Max For

Software Engineering: Qwen 3.7-Max scores 80% on SWE-bench Verified — ranked #7 of 13 models tracked here. It resolves real GitHub issues, writes production-quality code across multiple languages, and handles multi-step agentic coding workflows — a strong choice for AI-assisted software development teams.
Scientific & Technical Reasoning: At 92% on GPQA Diamond (#4 of 14 models), Qwen 3.7-Max exceeds the ~65% human PhD-expert baseline on graduate-level biology, chemistry, and physics questions. Use it for scientific literature synthesis, hypothesis evaluation, medical and legal Q&A, and multi-discipline research tasks where deep domain knowledge matters.
Agentic CLI Automation: Qwen 3.7-Max achieves 69% on Terminal-Bench (#3 of 8 models), making it competent for common shell scripting, command-line workflows, and light system administration tasks inside agentic pipelines.
Long-Document & Codebase Analysis: With a 1M-token context window, Qwen 3.7-Max can ingest entire software repositories, long legal contracts, book-length research reports, or extensive conversation histories in a single prompt — enabling deep document Q&A, cross-file codebase reasoning, and comprehensive summarisation without chunking heuristics or RAG pipelines.
Competitive Programming: Qwen 3.7-Max scores 91% on LiveCodeBench (#2 of 5 models), a contamination-resistant benchmark continuously refreshed with new competitive programming problems. At this level it handles advanced data structures, graph algorithms, and interview-level challenges with high reliability.

Strengths & Limitations

Strengths

Strong software engineering — 80% SWE-bench Verified
Graduate-level science reasoning — 92% GPQA Diamond
Competitive programming — 91% LiveCodeBench
Composite intelligence — 56 pts AA Intelligence Index (independent)
Very long documents and large codebases (1M context)

Limitations

Closed-weight — cannot be self-hosted or fine-tuned on private data

More to Compare

Related AI Models

Browse the Full AI Model Leaderboard

Compare all 24 models across 11 benchmarks — sortable, sourced, and updated June 2026.

← Back to AI Leaderboard Try in FlowHunt

Frequently asked questions

: Qwen 3.7-Max is a top-tier frontier AI model, developed by Alibaba and released in 2026-05. It is best known for real-world software engineering performance, scoring 80.4% on SWE-bench Verified.
: Qwen 3.7-Max is a proprietary closed-weight model. Its weights are not publicly available — access is through the Alibaba API only.
: Qwen 3.7-Max supports a 1M-token context window, large enough to hold entire codebases, lengthy technical documents, or extended agentic sessions without truncation.
: Qwen 3.7-Max has been evaluated on: SWE-bench Verified (80.4%), GPQA Diamond (92.4%), MMLU-Pro (89.6%), LiveCodeBench (91.6%), Terminal-Bench (69.7%), HLE (41.4%), AA Intelligence Index (56.6 pts). Scores tagged SR are self-reported by the provider; scores tagged 3P or AA have been independently verified by third parties.
: Yes — Qwen 3.7-Max is directly available in FlowHunt. You can use it to build AI agents, automated workflows, chatbots, and document processing pipelines without any additional setup.
: You can compare Qwen 3.7-Max against all 24 models tracked on the FlowHunt AI Leaderboard using the sortable benchmark table. The Benchmark Rankings section on this page shows Qwen 3.7-Max's position on each benchmark it has been evaluated on.

Learn more

Qwen 3.7-Plus — Benchmarks, Capabilities, and Use Cases

Qwen 3.7-Plus is a proprietary AI model from Alibaba, classified as Advanced tier with a 1M tokens context window. It is available directly in FlowHunt. Explore...

Jun 1, 2026 3 min read

MiniMax M3 — Benchmarks, Capabilities, and Use Cases

MiniMax M3 is a open-weight AI model from MiniMax (MoE (undisclosed)), classified as Frontier tier with a 1M tokens context window. It is available directly in ...

Jun 1, 2026 4 min read

Nemotron 3 Ultra — Benchmarks, Capabilities, and Use Cases

Nemotron 3 Ultra is a open-weight AI model from NVIDIA (55B/550B MoE), classified as Frontier tier with a 262K tokens context window. It is available directly i...

Jun 4, 2026 3 min read