The AI arena is free today

Open Superagent

Qwen3.7-Plus vs Qwen3.8-27B

Qwen3.7-Plus and Qwen3.8-27B are closely matched at 42.7 and 45.2 on the LLM Stats Score.

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

Which is better?

Qwen3.7-Plus and Qwen3.8-27B are closely matched on the overall LLM Stats Score at 42.7 and 45.2.

In the 16 individual benchmarks reported for both models, Qwen3.8-27B wins 11; this is a narrower head-to-head signal than the composite indexes.

Qwen3.7-Plus also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Qwen3.7-Plus

  • you process long inputs — it offers a 1,000,000 token context window

Choose Qwen3.8-27B

  • your work emphasizes agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 11 of 16 exact shared results
  • you want the most recent training data — it shipped Aug 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Qwen3.7-Plus
Alibaba Cloud / Qwen Team
Qwen3.8-27B
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
42.7
#44
45.2
#30
Reasoning
43.1
#39
44.8
#30
Coding
30.8
#47
31.6
#39
Agents
24.1
#47
30.4
#31
Cost, coverage & limits
Benchmark wins
5 of 16
11 of 16
Input price
$0.32 / M
— / M
Output price
$1.28 / M
— / M
Context window
1,000,000
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

5 shared
Index
Qwen3.7-Plus
Qwen3.8-27B
Math
39.5#15
31.0#68
Vision
32.2#21
33.1#18
Tool use
23.8#38
22.7#42
Multimodal
35.0#11
36.9#6
Productivity
-3.7#13
5.5#10
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

70 reported for Qwen3.7-Plus · 26 for Qwen3.8-27B

16 shared

Qwen3.7-Plus outperforms in 5 benchmarks (ERQA, GPQA, Humanity's Last Exam, OmniDocBench 1.5, RealWorldQA), while Qwen3.8-27B is better at 11 benchmarks (AndroidWorld, BabyVision, CharXiv-R, ClawEval-MM, CoWorkBench, IFBench, LiveCodeBench v6, MathVision, NL2Repo, OSWorld-Verified, SWE-Bench Pro).

Qwen3.8-27B shows notably better performance in the majority of benchmarks.

Mon Sep 07 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Qwen3.7-Plus accepts 1,000,000 input tokens compared to Qwen3.8-27B's 262,144 tokens. Qwen3.8-27B can generate longer responses up to 131,072 tokens, while Qwen3.7-Plus is limited to 65,536 tokens.

Alibaba Cloud / Qwen Team
Qwen3.7-Plus
Input1,000,000 tokens
Output65,536 tokens
Alibaba Cloud / Qwen Team
Qwen3.8-27B
Input262,144 tokens
Output131,072 tokens
Mon Sep 07 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Qwen3.7-Plus and Qwen3.8-27B support multimodal inputs.

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

Qwen3.7-Plus

Text
Images
Audio
Video

Qwen3.8-27B

Text
Images
Audio
Video

License

Usage and distribution terms

Qwen3.7-Plus is licensed under a proprietary license, while Qwen3.8-27B uses Apache 2.0.

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

Qwen3.7-Plus

Proprietary

Closed source

Qwen3.8-27B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Qwen3.7-Plus was released on 2026-05-31, while Qwen3.8-27B was released on 2026-08-14.

Qwen3.8-27B is 3 months newer than Qwen3.7-Plus.

Qwen3.7-Plus

May 31, 2026

3 months ago

Qwen3.8-27B

Aug 14, 2026

3 weeks ago

2mo 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

Qwen3.7-Plus is available from Together, Fireworks. Qwen3.8-27B is available from FriendliAI.

Qwen3.7-Plus

together logo
Together
Input Price:Input: $0.32/1MOutput Price:Output: $1.28/1M
fireworks logo
Fireworks
Input Price:Input: $0.40/1MOutput Price:Output: $1.60/1M

Qwen3.8-27B

friendli logo
FriendliAI
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Qwen3.7-Plus and Qwen3.8-27B side-by-side, then vote on the output you prefer.

Qwen3.7-Plus
✓ Preferred
Qwen3.8-27B
Open in Playground

FAQ

Common questions about Qwen3.7-Plus vs Qwen3.8-27B.

Which is better, Qwen3.7-Plus or Qwen3.8-27B?

Qwen3.7-Plus and Qwen3.8-27B are closely matched on the LLM Stats Score at 42.7 and 45.2. Qwen3.7-Plus 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 capability indexes, individual benchmarks, pricing, and limits above.

How does Qwen3.7-Plus compare to Qwen3.8-27B in benchmarks?

Qwen3.7-Plus scores IFEval: 94.6%, MMLU-Redux: 94.5%, HMMT Feb 26: 92.9%, MRCR v2: 91.7%, OmniDocBench 1.5: 91.4%. 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 Qwen3.7-Plus and Qwen3.8-27B?

Qwen3.7-Plus supports 1.0M tokens and Qwen3.8-27B supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Qwen3.7-Plus and Qwen3.8-27B?

Key differences include LLM Stats Score (42.7 vs 45.2), context window (1.0M vs 262K), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Related comparisons