Alibaba

Qwen3.5 397B-A17BOpen

Name: Qwen3.5 397B-A17B
Price: 2 USD
Rating: 23.9 (8 reviews)
Author: Alibaba

Open-weights Qwen MoE flagship with 17B active parameters.

#514released Feb 9, 2026·Open Weights·397B (17B active MoE)

text262.1K ctx

API providers Get API Key →Leaderboard

Intelligence

23.9 #514

AAQI 34.0

Output Speed

71 t/s

TTFT 2.37 s · ITL 14.1 ms/tok

Blended price (3:1)

$0.875 /1M

In $0.5/M · Out $2/M

Context

262.1K

≈ 655 A4 pages · max out 8,192

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Qwen3.5 397B-A17B

Claude Mythos Preview (#1)

Average (68)

Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.

API deployment

Compare hosts & latency

Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI

View providers matrix →

Scores by Source

Arena.ai ↗

1442.0

#75 · 61.8k votes · ±4

Artificial Analysis ↗

Category Scores

Value97.0 Long Context87.5 Math45.3 Knowledge29.2 Reasoning29.0 Coding11.5 Speed10.2 Agentic0.0

Benchmark Results

Ifeval92.6%

Multilingual MMLU88.5%GPQA Diamond88.4%MMLU-Pro87.8%SWE-Bench Verified76.4%

Browsecomp69%

Toolathlon38.3%Humanity’s Last Exam28.7%

Model Details

Release date

Feb 9, 2026

Parameters

397B (17B active MoE)

License

Open Weights

Context Window

262,100 tokens

Input Price

$0.5/M

Output Price

$2/M

Output Speed

71 t/s

Time to First Token

2.37 s

Estimated monthly bill

Monthly API requests: 100,000Avg input tokens: 1,500Avg output tokens: 500Prompt cache hit rate: 50%

Estimated monthly spend

$0.00

Calculating savings vs GPT-4o...

Cite & embed

GitHub Markdown badge

Loading badge markdown...

BibTeX

@misc{llmpodium2026qwen35397b,
  title = {Benchmark Analysis and Intelligence Evaluation of Qwen3.5 397B-A17B},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/qwen3-5-397b}
}

Embed Score Badge

Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.

Preview

Markdown

Loading badge snippet...

HTML

Loading badge snippet...

More from Alibaba

Alternative Models

Closest alternatives to Qwen3.5 397B-A17B based on capabilities, pricing, and benchmark scores.

Qwen3.8 Max

Alibaba · Proprietary