The AI arena is free today

Open Superagent

DeepSeek-V4.1-Flash vs Hy4 preview

DeepSeek-V4.1-Flash and Hy4 preview are closely matched at 51.8 and 51.0 on the LLM Stats Score.

DeepSeek · Tencent · Updated for 2026

Which is better?

DeepSeek-V4.1-Flash and Hy4 preview are closely matched on the overall LLM Stats Score at 51.8 and 51.0.

In the 9 individual benchmarks reported for both models, DeepSeek-V4.1-Flash wins 6; 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 DeepSeek-V4.1-Flash

  • your work emphasizes agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 6 of 9 exact shared results
  • you want the most recent training data — it shipped Sep 2026

Choose Hy4 preview

  • you are already invested in the Tencent ecosystem

At a glance

The differences that matter most.

DeepSeek-V4.1-Flash
DeepSeek
Hy4 preview
Tencent
Core performance indexes
LLM Stats Score
51.8
#13
51.0
#14
Reasoning
48.9
#18
50.8
#10
Coding
44.2
#5
39.7
#14
Agents
41.1
#4
36.7
#16
Cost, coverage & limits
Benchmark wins
6 of 9
3 of 9
Input price
$0.22 / M
— / M
Output price
$0.66 / M
— / M
Context window
1,040,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
DeepSeek-V4.1-Flash
Hy4 preview
Math
35.2#43
41.0#11
Tool use
34.8#2
30.9#14
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

20 reported for DeepSeek-V4.1-Flash · 32 for Hy4 preview

9 shared

DeepSeek-V4.1-Flash outperforms in 6 benchmarks (Agents' Last Exam, AutomationBench, CyberGym, NL2Repo, Program Bench, Terminal-Bench 2.1), while Hy4 preview is better at 3 benchmarks (GPQA, Humanity's Last Exam (no tools, text-only), MathArena Apex).

DeepSeek-V4.1-Flash shows notably better performance in the majority of benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

6.8B diff

Hy4 preview has 6.8B more parameters than DeepSeek-V4.1-Flash, making it 0.9% larger.

DeepSeek
DeepSeek-V4.1-Flash
763.2Bparameters
Tencent
Hy4 preview
770.0Bparameters
763.2B
DeepSeek-V4.1-Flash
770.0B
Hy4 preview

Context Window

Maximum input and output token capacity

Only DeepSeek-V4.1-Flash specifies input context (1,040,000 tokens). Only DeepSeek-V4.1-Flash specifies output context (393,216 tokens).

DeepSeek
DeepSeek-V4.1-Flash
Input1,040,000 tokens
Output393,216 tokens
Tencent
Hy4 preview
Input- tokens
Output- tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

DeepSeek-V4.1-Flash supports multimodal inputs, whereas Hy4 preview does not.

DeepSeek-V4.1-Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

DeepSeek-V4.1-Flash

Text
Images
Audio
Video

Hy4 preview

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V4.1-Flash is licensed under MIT, while Hy4 preview uses Apache 2.0.

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

DeepSeek-V4.1-Flash

MIT

Open weights

Hy4 preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V4.1-Flash was released on 2026-09-10, while Hy4 preview was released on 2026-08-28.

DeepSeek-V4.1-Flash is 0 month newer than Hy4 preview.

DeepSeek-V4.1-Flash

Sep 10, 2026

1 weeks ago

1w newer
Hy4 preview

Aug 28, 2026

3 weeks 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 DeepSeek-V4.1-Flash and Hy4 preview side-by-side, then vote on the output you prefer.

DeepSeek-V4.1-Flash
✓ Preferred
Hy4 preview
Open in Playground

FAQ

Common questions about DeepSeek-V4.1-Flash vs Hy4 preview.

Which is better, DeepSeek-V4.1-Flash or Hy4 preview?

DeepSeek-V4.1-Flash and Hy4 preview are closely matched on the LLM Stats Score at 51.8 and 51.0. DeepSeek-V4.1-Flash is made by DeepSeek and Hy4 preview is made by Tencent. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V4.1-Flash compare to Hy4 preview in benchmarks?

DeepSeek-V4.1-Flash scores CodeForces: 100.0%, GPQA: 90.9%, Terminal-Bench 2.1: 90.6%, BabyVision: 89.6%, CyberGym: 88.1%. Hy4 preview scores GPQA: 92.3%, Terminal-Bench 2.1: 85.4%, WideSearch: 83.9%, MCP Atlas: 83.7%, SWE-bench Multilingual: 82.9%.

What are the context window sizes for DeepSeek-V4.1-Flash and Hy4 preview?

DeepSeek-V4.1-Flash supports 1.0M tokens and Hy4 preview supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V4.1-Flash and Hy4 preview?

Key differences include LLM Stats Score (51.8 vs 51.0), multimodal support (yes vs no), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4.1-Flash and Hy4 preview?

DeepSeek-V4.1-Flash is developed by DeepSeek and Hy4 preview is developed by Tencent.

Related comparisons