The AI arena is free today

Open Playground

Model Comparison

Qwen3.6-35B-A3B vs Qwen3.8 MaxWhich is better in 2026?

Qwen3.8 Max significantly outperforms across most benchmarks.

Verdict: Qwen3.6-35B-A3B vs Qwen3.8 Max — which is better?

Qwen3.6-35B-A3B (by Alibaba Cloud / Qwen Team) and Qwen3.8 Max (by Alibaba Cloud / Qwen Team) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Qwen3.6-35B-A3B outperforms in 0 benchmarks, while Qwen3.8 Max is better at 9 benchmarks (GPQA, Humanity's Last Exam, LVBench, MMMU-Pro, NL2Repo, RealWorldQA, SkillsBench, SWE-Bench Pro, VideoMME w sub.). Qwen3.8 Max significantly outperforms across most benchmarks.

Choose Qwen3.6-35B-A3B if…

  • you need open weights you can self-host or fine-tune

Choose Qwen3.8 Max if…

  • you want the strongest raw capability — it leads on 9 of 9 shared benchmarks
  • you want the most recent training data — it shipped Aug 2026

Performance Benchmarks

Comparative analysis across standard metrics

9 benchmarks

Qwen3.6-35B-A3B outperforms in 0 benchmarks, while Qwen3.8 Max is better at 9 benchmarks (GPQA, Humanity's Last Exam, LVBench, MMMU-Pro, NL2Repo, RealWorldQA, SkillsBench, SWE-Bench Pro, VideoMME w sub.).

Qwen3.8 Max significantly outperforms across most benchmarks.

Fri Aug 07 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

2365.0B diff

Qwen3.8 Max has 2365.0B more parameters than Qwen3.6-35B-A3B, making it 6757.1% larger.

Alibaba Cloud / Qwen Team
Qwen3.6-35B-A3B
35.0Bparameters
Alibaba Cloud / Qwen Team
Qwen3.8 Max
2.4Tparameters
35.0B
Qwen3.6-35B-A3B
2400.0B
Qwen3.8 Max

Input Capabilities

Supported data types and modalities

Both Qwen3.6-35B-A3B and Qwen3.8 Max support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Qwen3.6-35B-A3B

Text
Images
Audio
Video

Qwen3.8 Max

Text
Images
Audio
Video

License

Usage and distribution terms

Qwen3.6-35B-A3B is licensed under Apache 2.0, while Qwen3.8 Max uses a proprietary license.

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

Qwen3.6-35B-A3B

Apache 2.0

Open weights

Qwen3.8 Max

Proprietary

Closed source

Release Timeline

When each model was launched

Qwen3.6-35B-A3B was released on 2026-04-16, while Qwen3.8 Max was released on 2026-08-02.

Qwen3.8 Max is 4 months newer than Qwen3.6-35B-A3B.

Qwen3.6-35B-A3B

Apr 16, 2026

3 months ago

Qwen3.8 Max

Aug 2, 2026

5 days 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Alibaba Cloud / Qwen Team

Qwen3.6-35B-A3B

View details

Alibaba Cloud / Qwen Team

Has open weights
Alibaba Cloud / Qwen Team

Qwen3.8 Max

View details

Alibaba Cloud / Qwen Team

Higher GPQA score (92.6% vs 86.0%)
Higher Humanity's Last Exam score (43.6% vs 21.4%)
Higher LVBench score (81.8% vs 71.4%)
Higher MMMU-Pro score (82.3% vs 75.3%)
Higher NL2Repo score (55.9% vs 29.4%)
Higher RealWorldQA score (88.0% vs 85.3%)
Higher SkillsBench score (70.2% vs 28.7%)
Higher SWE-Bench Pro score (67.7% vs 49.5%)
Higher VideoMME w sub. score (90.4% vs 86.6%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Qwen3.6-35B-A3B and Qwen3.8 Max side-by-side, then vote on the output you prefer.

Qwen3.6-35B-A3B
✓ Preferred
Qwen3.8 Max
Open in Playground
AI Model Comparison Table
Feature
Alibaba Cloud / Qwen Team
Qwen3.6-35B-A3B
Alibaba Cloud / Qwen Team
Qwen3.8 Max

FAQ

Common questions about Qwen3.6-35B-A3B vs Qwen3.8 Max.

Which is better, Qwen3.6-35B-A3B or Qwen3.8 Max?

Qwen3.8 Max significantly outperforms across most benchmarks. Qwen3.6-35B-A3B is made by Alibaba Cloud / Qwen Team and Qwen3.8 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 Qwen3.6-35B-A3B compare to Qwen3.8 Max in benchmarks?

Qwen3.6-35B-A3B scores MMLU-Redux: 93.3%, MMBench-V1.1: 92.8%, AI2D: 92.7%, AIME 2026: 92.7%, RefCOCO-avg: 92.0%. Qwen3.8 Max scores PaperBench: 93.0%, GPQA: 92.6%, VideoMME w sub.: 90.4%, RealWorldQA: 88.0%, Terminal-Bench 2.1: 86.6%.

What are the main differences between Qwen3.6-35B-A3B and Qwen3.8 Max?

Key differences include licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.