Model Comparison

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

Qwen3.6 Plus significantly outperforms across most benchmarks.

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

Qwen3.6-35B-A3B (by Alibaba Cloud / Qwen Team) and Qwen3.6 Plus (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 Qwen3.6 Plus is better at 39 benchmarks (AI2D, AIME 2026, CC-OCR, C-Eval, CharXiv-R, Claw-Eval, DeepPlanning, GDPval-AA, GPQA, HMMT 2025, HMMT25, HMMT Feb 26, Humanity's Last Exam, IMO-AnswerBench, LiveCodeBench v6, MCP Atlas, MCP-Mark, MLVU, MMLU-Pro, MMLU-Redux, MMMU, MMMU-Pro, NL2Repo, ODinW, OmniDocBench 1.5, RealWorldQA, RefCOCO-avg, SimpleVQA, SkillsBench, SuperGPQA, SWE-bench Multilingual, SWE-Bench Pro, SWE-Bench Verified, TAU3-Bench, Terminal-Bench 2.0, Toolathlon, VideoMMMU, VITA-Bench, WideSearch). Qwen3.6 Plus significantly outperforms across most benchmarks.

Choose Qwen3.6-35B-A3B if…

  • you want the most recent training data — it shipped Apr 2026
  • you need open weights you can self-host or fine-tune

Choose Qwen3.6 Plus if…

  • you want the strongest raw capability — it leads on 39 of 39 shared benchmarks

Performance Benchmarks

Comparative analysis across standard metrics

39 benchmarks

Qwen3.6-35B-A3B outperforms in 0 benchmarks, while Qwen3.6 Plus is better at 39 benchmarks (AI2D, AIME 2026, CC-OCR, C-Eval, CharXiv-R, Claw-Eval, DeepPlanning, GDPval-AA, GPQA, HMMT 2025, HMMT25, HMMT Feb 26, Humanity's Last Exam, IMO-AnswerBench, LiveCodeBench v6, MCP Atlas, MCP-Mark, MLVU, MMLU-Pro, MMLU-Redux, MMMU, MMMU-Pro, NL2Repo, ODinW, OmniDocBench 1.5, RealWorldQA, RefCOCO-avg, SimpleVQA, SkillsBench, SuperGPQA, SWE-bench Multilingual, SWE-Bench Pro, SWE-Bench Verified, TAU3-Bench, Terminal-Bench 2.0, Toolathlon, VideoMMMU, VITA-Bench, WideSearch).

Qwen3.6 Plus significantly outperforms across most benchmarks.

Fri Jul 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Qwen3.6 Plus specifies input context (1,000,000 tokens). Only Qwen3.6 Plus specifies output context (65,536 tokens).

Alibaba Cloud / Qwen Team
Qwen3.6-35B-A3B
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
Qwen3.6 Plus
Input1,000,000 tokens
Output65,536 tokens
Fri Jul 17 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Qwen3.6-35B-A3B and Qwen3.6 Plus 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

Qwen3.6 Plus

Text
Images
Audio
Video

License

Usage and distribution terms

Qwen3.6-35B-A3B is licensed under Apache 2.0, while Qwen3.6 Plus 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

Qwen3.6 Plus

Proprietary

Closed source

Release Timeline

When each model was launched

Qwen3.6-35B-A3B was released on 2026-04-16, while Qwen3.6 Plus was released on 2026-03-31.

Qwen3.6-35B-A3B is 1 month newer than Qwen3.6 Plus.

Qwen3.6-35B-A3B

Apr 16, 2026

3 months ago

2w newer
Qwen3.6 Plus

Mar 31, 2026

3 months ago

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

Qwen3.6 Plus

View details

Alibaba Cloud / Qwen Team

Larger context window (1,000,000 tokens)
Higher AI2D score (94.4% vs 92.7%)
Higher AIME 2026 score (95.3% vs 92.7%)
Higher CC-OCR score (83.4% vs 81.9%)
Higher C-Eval score (93.3% vs 90.0%)
Higher CharXiv-R score (81.5% vs 78.0%)
Higher Claw-Eval score (58.7% vs 50.0%)
Higher DeepPlanning score (41.5% vs 25.9%)
Higher GDPval-AA score (38.7% vs 35.2%)
Higher GPQA score (90.4% vs 86.0%)
Higher HMMT 2025 score (96.7% vs 90.7%)
Higher HMMT25 score (94.6% vs 89.1%)
Higher HMMT Feb 26 score (87.8% vs 83.6%)
Higher Humanity's Last Exam score (28.8% vs 21.4%)
Higher IMO-AnswerBench score (83.8% vs 78.9%)
Higher LiveCodeBench v6 score (87.1% vs 80.4%)
Higher MCP Atlas score (74.1% vs 62.8%)
Higher MCP-Mark score (48.2% vs 37.0%)
Higher MLVU score (86.7% vs 86.2%)
Higher MMLU-Pro score (88.5% vs 85.2%)
Higher MMLU-Redux score (94.5% vs 93.3%)
Higher MMMU score (86.0% vs 81.7%)
Higher MMMU-Pro score (78.8% vs 75.3%)
Higher NL2Repo score (37.9% vs 29.4%)
Higher ODinW score (51.8% vs 50.8%)
Higher OmniDocBench 1.5 score (91.2% vs 89.9%)
Higher RealWorldQA score (85.4% vs 85.3%)
Higher RefCOCO-avg score (93.5% vs 92.0%)
Higher SimpleVQA score (67.3% vs 58.9%)
Higher SkillsBench score (45.7% vs 28.7%)
Higher SuperGPQA score (71.6% vs 64.7%)
Higher SWE-bench Multilingual score (73.8% vs 67.2%)
Higher SWE-Bench Pro score (56.6% vs 49.5%)
Higher SWE-Bench Verified score (78.8% vs 73.4%)
Higher TAU3-Bench score (70.7% vs 67.2%)
Higher Terminal-Bench 2.0 score (61.6% vs 51.5%)
Higher Toolathlon score (39.8% vs 26.9%)
Higher VideoMMMU score (84.0% vs 83.7%)
Higher VITA-Bench score (44.3% vs 35.6%)
Higher WideSearch score (74.3% vs 60.1%)

Detailed Comparison

Interactive Arena

Judge for yourself.

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

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

FAQ

Common questions about Qwen3.6-35B-A3B vs Qwen3.6 Plus.

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

Qwen3.6 Plus significantly outperforms across most benchmarks. Qwen3.6-35B-A3B is made by Alibaba Cloud / Qwen Team and Qwen3.6 Plus 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 Qwen3.6 Plus 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%. Qwen3.6 Plus scores CountBench: 97.6%, V*: 96.9%, HMMT 2025: 96.7%, AIME 2026: 95.3%, HMMT25: 94.6%.

What are the context window sizes for Qwen3.6-35B-A3B and Qwen3.6 Plus?

Qwen3.6-35B-A3B supports an unknown number of tokens and Qwen3.6 Plus 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 Qwen3.6-35B-A3B and Qwen3.6 Plus?

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

Related comparisons