The AI arena is free today

Open Superagent

Qwen3.8-Flash-Next vs Step-3.5-Flash

Qwen3.8-Flash-Next leads the LLM Stats Score 49.7 to 37.3.

Alibaba Cloud / Qwen Team · StepFun · Updated for 2026

Which is better?

Qwen3.8-Flash-Next leads the overall LLM Stats Score 49.7 to 37.3, ranking #15 overall.

In the 1 individual benchmarks reported for both models, Qwen3.8-Flash-Next wins 1; this is a narrower head-to-head signal than the composite indexes.

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

Choose Qwen3.8-Flash-Next

  • overall performance matters — it scores 49.7 and ranks #15 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Aug 2026

Choose Step-3.5-Flash

  • you want predictable pricing at $0.10/M input and $0.40/M output

At a glance

The differences that matter most.

Qwen3.8-Flash-Next
Alibaba Cloud / Qwen Team
Step-3.5-Flash
StepFun
Core performance indexes
LLM Stats Score
49.7
#15
37.3
#61
Reasoning
49.3
#15
37.3
#62
Coding
36.6
#18
20.4
#88
Agents
35.5
#13
15.3
#74
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
— / M
$0.10 / M
Output price
— / M
$0.40 / M
Context window
—
65,536

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Qwen3.8-Flash-Next
Step-3.5-Flash
Math
32.7#54
33.8#50
Tool use
31.6#9
12.9#93
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

22 reported for Qwen3.8-Flash-Next · 7 for Step-3.5-Flash

1 shared

Qwen3.8-Flash-Next outperforms in 1 benchmarks (LiveCodeBench v6), while Step-3.5-Flash is better at 0 benchmarks.

Qwen3.8-Flash-Next significantly outperforms across most benchmarks.

Tue Sep 01 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

71.0B diff

Step-3.5-Flash has 71.0B more parameters than Qwen3.8-Flash-Next, making it 56.8% larger.

Alibaba Cloud / Qwen Team
Qwen3.8-Flash-Next
125.0Bparameters
StepFun
Step-3.5-Flash
196.0Bparameters
125.0B
Qwen3.8-Flash-Next
196.0B
Step-3.5-Flash

Context Window

Maximum input and output token capacity

Only Step-3.5-Flash specifies input context (65,536 tokens). Only Step-3.5-Flash specifies output context (8,192 tokens).

Alibaba Cloud / Qwen Team
Qwen3.8-Flash-Next
Input- tokens
Output- tokens
StepFun
Step-3.5-Flash
Input65,536 tokens
Output8,192 tokens
Tue Sep 01 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen3.8-Flash-Next supports multimodal inputs, whereas Step-3.5-Flash does not.

Qwen3.8-Flash-Next can handle both text and other forms of data like images, making it suitable for multimodal applications.

Qwen3.8-Flash-Next

Text
Images
Audio
Video

Step-3.5-Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Qwen3.8-Flash-Next is licensed under Qwen Community License 1.0, while Step-3.5-Flash uses Apache 2.0.

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

Qwen3.8-Flash-Next

Qwen Community License 1.0

Open weights

Step-3.5-Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

Qwen3.8-Flash-Next was released on 2026-08-26, while Step-3.5-Flash was released on 2026-02-02.

Qwen3.8-Flash-Next is 7 months newer than Step-3.5-Flash.

Qwen3.8-Flash-Next

Aug 26, 2026

5 days ago

6mo newer
Step-3.5-Flash

Feb 2, 2026

7 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→

Judge for yourself.

Run your own prompts against Qwen3.8-Flash-Next and Step-3.5-Flash side-by-side, then vote on the output you prefer.

Qwen3.8-Flash-Next
✓ Preferred
Step-3.5-Flash
Open in Playground

FAQ

Common questions about Qwen3.8-Flash-Next vs Step-3.5-Flash.

Which is better, Qwen3.8-Flash-Next or Step-3.5-Flash?

Qwen3.8-Flash-Next leads the LLM Stats Score 49.7 to 37.3. Qwen3.8-Flash-Next is made by Alibaba Cloud / Qwen Team and Step-3.5-Flash is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Qwen3.8-Flash-Next compare to Step-3.5-Flash in benchmarks?

Qwen3.8-Flash-Next scores MathVision: 95.7%, LiveCodeBench v6: 91.9%, GPQA: 91.7%, CharXiv-R: 90.6%, RealWorldQA: 88.5%. Step-3.5-Flash scores AIME 2025: 97.3%, Tau-bench: 88.2%, LiveCodeBench v6: 86.4%, IMO-AnswerBench: 85.4%, SWE-Bench Verified: 74.4%.

What are the context window sizes for Qwen3.8-Flash-Next and Step-3.5-Flash?

Qwen3.8-Flash-Next supports an unknown number of tokens and Step-3.5-Flash supports 66K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Qwen3.8-Flash-Next and Step-3.5-Flash?

Key differences include LLM Stats Score (49.7 vs 37.3), multimodal support (yes vs no), licensing (Qwen Community License 1.0 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Qwen3.8-Flash-Next and Step-3.5-Flash?

Qwen3.8-Flash-Next is developed by Alibaba Cloud / Qwen Team and Step-3.5-Flash is developed by StepFun.

Related comparisons