Model Comparison

Qwen3.5-397B-A17B vs Qwen3.7 Max

Qwen3.7 Max significantly outperforms across most benchmarks. Qwen3.5-397B-A17B is 1.4x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

23 benchmarks

Qwen3.5-397B-A17B outperforms in 2 benchmarks (NOVA-63, VITA-Bench), while Qwen3.7 Max is better at 21 benchmarks (BFCL-V4, Global PIQA, GPQA, Humanity's Last Exam, IFBench, IFEval, IMO-AnswerBench, Include, LiveCodeBench v6, MAXIFE, MCP-Mark, MMLU-Pro, MMLU-ProX, MMLU-Redux, MMMLU, PolyMATH, SuperGPQA, SWE-bench Multilingual, SWE-Bench Verified, Terminal-Bench 2.0, WMT24++).

Qwen3.7 Max significantly outperforms across most benchmarks.

Tue May 26 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Qwen3.5-397B-A17B costs less

For input processing, Qwen3.5-397B-A17B ($0.60/1M tokens) is 2.1x cheaper than Qwen3.7 Max ($1.25/1M tokens).

For output processing, Qwen3.5-397B-A17B ($3.60/1M tokens) is 1.0x cheaper than Qwen3.7 Max ($3.75/1M tokens).

In conclusion, Qwen3.7 Max is more expensive than Qwen3.5-397B-A17B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers

Tue May 26 2026 • llm-stats.com

Qwen3.5-397B-A17B

Input tokens$0.60

Output tokens$3.60

Best providerNovita

Qwen3.7 Max

Input tokens$1.25

Output tokens$3.75

Best providerNovita

Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Qwen3.7 Max accepts 1,000,000 input tokens compared to Qwen3.5-397B-A17B's 262,144 tokens. Qwen3.7 Max can generate longer responses up to 65,536 tokens, while Qwen3.5-397B-A17B is limited to 64,000 tokens.

Qwen3.5-397B-A17B

Input262,144 tokens

Output64,000 tokens

Qwen3.7 Max

Input1,000,000 tokens

Output65,536 tokens

Tue May 26 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Qwen3.5-397B-A17B supports multimodal inputs, whereas Qwen3.7 Max does not.

Qwen3.5-397B-A17B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Qwen3.5-397B-A17B

Text

Images

Audio

Video

Qwen3.7 Max

Text

Images

Audio

Video

License

Usage and distribution terms

Qwen3.5-397B-A17B is licensed under Apache 2.0, while Qwen3.7 Max uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

Qwen3.5-397B-A17B

Apache 2.0

Open weights

Qwen3.7 Max

Proprietary

Closed source

Release Timeline

When each model was launched

Qwen3.5-397B-A17B was released on 2026-02-16, while Qwen3.7 Max was released on 2026-05-19.

Qwen3.7 Max is 3 months newer than Qwen3.5-397B-A17B.

Qwen3.5-397B-A17B

Feb 16, 2026

3 months ago

Qwen3.7 Max

May 19, 2026

1 weeks ago

3mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Qwen3.5-397B-A17B is available from Novita. Qwen3.7 Max is available from Novita, Together.

Qwen3.5-397B-A17B

Novita

Input Price:Input: $0.60/1MOutput Price:Output: $3.60/1M

Qwen3.7 Max

Novita

Input Price:Input: $1.25/1MOutput Price:Output: $3.75/1M

Together

Input Price:Input: $2.50/1MOutput Price:Output: $7.50/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Qwen3.5-397B-A17B

View details

Alibaba Cloud / Qwen Team

Supports multimodal inputs

Less expensive input tokens

Less expensive output tokens

Has open weights

Higher NOVA-63 score (59.1% vs 59.0%)

Higher VITA-Bench score (49.7% vs 47.9%)

Qwen3.7 Max

View details

Alibaba Cloud / Qwen Team

Larger context window (1,000,000 tokens)

Higher BFCL-V4 score (75.0% vs 72.9%)

Higher Global PIQA score (91.4% vs 89.8%)

Higher GPQA score (92.4% vs 88.4%)

Higher Humanity's Last Exam score (41.4% vs 28.7%)

Higher IFBench score (79.1% vs 76.5%)

Higher IFEval score (94.3% vs 92.6%)

Higher IMO-AnswerBench score (90.0% vs 80.9%)

Higher Include score (86.2% vs 85.6%)

Higher LiveCodeBench v6 score (91.6% vs 83.6%)

Higher MAXIFE score (89.2% vs 88.2%)

Higher MCP-Mark score (60.8% vs 46.1%)

Higher MMLU-Pro score (89.6% vs 87.8%)

Higher MMLU-ProX score (87.0% vs 84.7%)

Higher MMLU-Redux score (95.0% vs 94.9%)

Higher MMMLU score (90.3% vs 88.5%)

Higher PolyMATH score (86.5% vs 73.3%)

Higher SuperGPQA score (73.6% vs 70.4%)

Higher SWE-bench Multilingual score (78.3% vs 69.3%)

Higher SWE-Bench Verified score (80.4% vs 76.4%)

Higher Terminal-Bench 2.0 score (69.7% vs 52.5%)

Higher WMT24++ score (85.8% vs 78.9%)

Detailed Comparison

AI Model Comparison Table
Feature	Qwen3.5-397B-A17B	Qwen3.7 Max

FAQ

Common questions about Qwen3.5-397B-A17B vs Qwen3.7 Max.

Which is better, Qwen3.5-397B-A17B or Qwen3.7 Max?

Qwen3.7 Max significantly outperforms across most benchmarks. Qwen3.5-397B-A17B is made by Alibaba Cloud / Qwen Team and Qwen3.7 Max is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Qwen3.5-397B-A17B compare to Qwen3.7 Max in benchmarks?

Qwen3.5-397B-A17B scores MMLU-Redux: 94.9%, HMMT 2025: 94.8%, C-Eval: 93.0%, HMMT25: 92.7%, IFEval: 92.6%. Qwen3.7 Max scores HMMT Feb 26: 97.1%, Kernel Bench L3: 96.0%, MMLU-Redux: 95.0%, IFEval: 94.3%, GPQA: 92.4%.

Is Qwen3.5-397B-A17B cheaper than Qwen3.7 Max?

Qwen3.5-397B-A17B is 2.1x cheaper for input tokens. Qwen3.5-397B-A17B costs $0.60/M input and $3.60/M output via novita. Qwen3.7 Max costs $1.25/M input and $3.75/M output via novita.

What are the context window sizes for Qwen3.5-397B-A17B and Qwen3.7 Max?

Qwen3.5-397B-A17B supports 262K tokens and Qwen3.7 Max supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Qwen3.5-397B-A17B and Qwen3.7 Max?

Key differences include context window (262K vs 1.0M), input pricing ($0.60 vs $1.25/M), multimodal support (yes vs no), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.