The AI arena is free today

Open Superagent

Qwen3.5-35B-A3B vs Qwen3.8-27B

Qwen3.8-27B significantly outperforms across most benchmarks.

Alibaba Cloud / Qwen Team · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Qwen3.5-35B-A3B outperforms in 1 benchmarks (Humanity's Last Exam), while Qwen3.8-27B is better at 10 benchmarks (BabyVision, CharXiv-R, ERQA, GPQA, IFBench, LiveCodeBench v6, MathVision, OmniDocBench 1.5, OSWorld-Verified, RealWorldQA). Qwen3.8-27B significantly outperforms across most benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Qwen3.5-35B-A3B

  • you want predictable pricing at $0.25/M input and $2.00/M output

Choose Qwen3.8-27B

  • you want the strongest raw capability — it leads on 10 of 11 shared benchmarks
  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

Benchmark wins
1 of 11
10 of 11
Input price
$0.25 / M
— / M
Output price
$2.00 / M
— / M
Context window
262,144
Released
Feb 2026
Aug 2026
License
Apache 2.0
Apache 2.0

Performance Benchmarks

Comparative analysis across standard metrics

11 benchmarks

Qwen3.5-35B-A3B outperforms in 1 benchmarks (Humanity's Last Exam), while Qwen3.8-27B is better at 10 benchmarks (BabyVision, CharXiv-R, ERQA, GPQA, IFBench, LiveCodeBench v6, MathVision, OmniDocBench 1.5, OSWorld-Verified, RealWorldQA).

Qwen3.8-27B significantly outperforms across most benchmarks.

Tue Aug 25 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

7.2B diff

Qwen3.5-35B-A3B has 7.2B more parameters than Qwen3.8-27B, making it 26.0% larger.

Alibaba Cloud / Qwen Team
Qwen3.5-35B-A3B
35.0Bparameters
Alibaba Cloud / Qwen Team
Qwen3.8-27B
27.8Bparameters
35.0B
Qwen3.5-35B-A3B
27.8B
Qwen3.8-27B

Context Window

Maximum input and output token capacity

Only Qwen3.5-35B-A3B specifies input context (262,144 tokens). Only Qwen3.5-35B-A3B specifies output context (65,000 tokens).

Alibaba Cloud / Qwen Team
Qwen3.5-35B-A3B
Input262,144 tokens
Output65,000 tokens
Alibaba Cloud / Qwen Team
Qwen3.8-27B
Input- tokens
Output- tokens
Tue Aug 25 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Qwen3.5-35B-A3B and Qwen3.8-27B support multimodal inputs.

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

Qwen3.5-35B-A3B

Text
Images
Audio
Video

Qwen3.8-27B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Qwen3.5-35B-A3B

Apache 2.0

Open weights

Qwen3.8-27B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Qwen3.5-35B-A3B was released on 2026-02-24, while Qwen3.8-27B was released on 2026-08-14.

Qwen3.8-27B is 6 months newer than Qwen3.5-35B-A3B.

Qwen3.5-35B-A3B

Feb 24, 2026

6 months ago

Qwen3.8-27B

Aug 14, 2026

1 weeks ago

5mo 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

Judge for yourself.

Run your own prompts against Qwen3.5-35B-A3B and Qwen3.8-27B side-by-side, then vote on the output you prefer.

Qwen3.5-35B-A3B
✓ Preferred
Qwen3.8-27B
Open in Playground

FAQ

Common questions about Qwen3.5-35B-A3B vs Qwen3.8-27B.

Which is better, Qwen3.5-35B-A3B or Qwen3.8-27B?

Qwen3.8-27B significantly outperforms across most benchmarks. Qwen3.5-35B-A3B is made by Alibaba Cloud / Qwen Team and Qwen3.8-27B 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 Qwen3.5-35B-A3B compare to Qwen3.8-27B in benchmarks?

Qwen3.5-35B-A3B scores CountBench: 97.8%, VLMsAreBlind: 97.0%, MMLU-Redux: 93.3%, V*: 92.7%, AI2D: 92.6%. Qwen3.8-27B scores MathVision: 94.6%, OmniDocBench 1.5: 91.1%, LiveCodeBench v6: 90.3%, CharXiv-R: 90.2%, GPQA: 89.2%.

What are the context window sizes for Qwen3.5-35B-A3B and Qwen3.8-27B?

Qwen3.5-35B-A3B supports 262K tokens and Qwen3.8-27B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.