AI Tools Review

Qwen4 Max

By Alibaba

Released: 2026-11-16

LLM
Alibaba
Paid
New

Qwen4 Max is Alibaba's AI model, released 16/11/2026. Alibaba's launch post compares Qwen4-Max with Qwen3.8-Max-0902, Claude Opus 5.5, GPT-6.1 Sol, GPT-6 Astra and Kimi K3.1 across 16 benchmarks. It leads on DeepSWE v1.1 (75.7), Agents' Last Exam v1.1, HLAB-Vals legal work and BioMysteryBench, and trails Claude Opus 5.5 and Kimi K3.1 clearly on Terminal-Bench 4.0 and ProgramBench. The launch page is script-rendered and could not be fetched, so every row here comes from the site article that reads Alibaba's chart; some chart rows are third-party scores cited by Alibaba.

Visit Qwen4 Max

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does Qwen4-Max score on independent benchmarks?

Qwen4-Max ranks #13 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 42.9, as measured on 22 November 2026.

Intelligence Index
42.9
AA v5.0.1
Coding Agent Index
n/a
Cost per task
$3.27
AA Intelligence Index task
Price per 1M tokens
$1.5 / $4.5
input / output

Where does Qwen4-Max rank against other models?

How does Qwen4-Max do on individual tests?

Evaluation (run by Artificial Analysis)Qwen4-MaxBest of any model
Terminal-Bench 4.048.5%67.2%
FrontierCode 2.026.5%48.8%
Humanity's Last Examn/a74.3%
GDPval-AA (Elo)18091866

How has Qwen4-Max's score changed over time?

We have tracked Qwen4-Max on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the Qwen4-Max system card report?

Alibaba's launch post compares Qwen4-Max with Qwen3.8-Max-0902, Claude Opus 5.5, GPT-6.1 Sol, GPT-6 Astra and Kimi K3.1 across 16 benchmarks. It leads on DeepSWE v1.1 (75.7), Agents' Last Exam v1.1, HLAB-Vals legal work and BioMysteryBench, and trails Claude Opus 5.5 and Kimi K3.1 clearly on Terminal-Bench 4.0 and ProgramBench. The launch page is script-rendered and could not be fetched, so every row here comes from the site article that reads Alibaba's chart; some chart rows are third-party scores cited by Alibaba.

These are Alibaba (Qwen)'s own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Source: Qwen4-Max: Your New Teammate Has Arrived (16/11/2026). Last checked 22/11/2026.

Coding

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
DeepSWE v1.1Agentic coding75.7%69.3%74.2%75.2%
CodeArenaWeb development1750 Elo167618161742
Terminal-Bench 4.0Effort level and harness not stated in the launch post48.5%38.9%59.6%56.1%
ProgramBench31.5%28%65%52.5%

Agents & tool use

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
AA-Briefcase v1.1Score cited from Artificial Analysis1686 Elo160518011555
JobBench68.5%65.3%75.4%66.2%
APEX-Agents v1.1Score cited from Mercor72.1%63.3%73.5%60%
HLAB-Vals-1.1 (legal)Score cited from the Vals Index21.3%15.4%9.2%6.3%
AutomationBench-AAScore cited from Artificial Analysis72.5%56.2%69.5%64.9%
Agents' Last Exam v1.1Separate panel in the launch chart; Qwen3.8-Max 27.9, Opus 5.5 43.4, Kimi K3.1 43.446.7%27.9%43.4%n/a
AgentArena (net improvement)Separate panel in the launch chart; Opus 5.5 18.27.5 scoren/a18.2n/a
Work360Alibaba-designed benchmark (26 domains, 182 subdomains, 721 fields); useful for comparing Qwen generations only52.69 score47.74n/an/a

Knowledge & science

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
BioMysteryBench85%84.1%81.9%84.4%
HealthBench Professional60%39.6%59.9%65.1%
Humanity's Last Exam51.7%43.9%59.8%54%

Multimodal

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
ChartographyChart understanding54.2%42%66.3%67.8%
Video-IndexVideo understanding68.1%63.2%74.8%73.8%

Safety & honesty

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
Last Secure Code Bench (function level, correct and secure)Share of functions both correct and secure31.8%22%n/an/a
Last Secure Code Bench (function, file and repository level)Share secure at all three levels14.7%8%n/an/a

Other

BenchmarkQwen4-MaxQwen3.8-MaxClaude Opus 5.5GPT-6.1 Sol
Base model: Knowledge (10 x bits per byte)Qwen4-Max-Base; lower is better; Alibaba in-house evaluation. Kimi-K3.1-Pro is a post-trained model so not like for like. GLM-5.3 is 5.874.86 BPB x105.6n/an/a
Base model: Code (10 x bits per byte)Qwen4-Max-Base; lower is better; Alibaba in-house evaluation. GLM-5.3 is 1.901.67 BPB x101.88n/an/a
Base model: QA (10 x bits per byte)Qwen4-Max-Base; lower is better; Alibaba in-house evaluation. GLM-5.3 is 3.202.94 BPB x103.1n/an/a
Base model: STEM (10 x bits per byte)Qwen4-Max-Base; lower is better; Alibaba in-house evaluation. GLM-5.3 is 3.242.7 BPB x103.04n/an/a

What did safety testing find for Qwen4-Max?

Safety level: No formal system card; vendor safety section in launch post

  • Last Secure Code Bench: share of functions both correct and secure rose from 22.0% to 31.8%; secure at function, file and repository level rose from 8% to 14.7%.
  • Alibaba says internal experts reviewed long agent runs, including the full chain of thought, and found no capabilities posing large-scale cybersecurity risks.
  • Alibaba says internal experts found no significant CBRN uplift risk, and that the model did not over-refuse.

Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our Qwen4-Max deep dive.

Alibaba Model Timeline

Qwen4 MaxCurrent

1M tokens context

Qwen3.7 Max

1M tokens context

Tongyi DeepResearch 30B A3B

131k tokens context

Specifications

pricing$1.5/$4.5 per 1M tokens (input/output)
context Window1M tokens