The AI arena is free today

Open Superagent

DeepSeek-V4-Pro-0813 vs Hy4 preview

DeepSeek-V4-Pro-0813 and Hy4 preview are closely matched at 52.9 and 51.5 on the LLM Stats Score.

DeepSeek · Tencent · Updated for 2026

Which is better?

DeepSeek-V4-Pro-0813 and Hy4 preview are closely matched on the overall LLM Stats Score at 52.9 and 51.5.

In the 9 individual benchmarks reported for both models, DeepSeek-V4-Pro-0813 wins 5; 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-Pro-0813

  • you value its reported benchmark strengths — it wins 5 of 9 exact shared results

Choose Hy4 preview

  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

DeepSeek-V4-Pro-0813
DeepSeek
Hy4 preview
Tencent
Core performance indexes
LLM Stats Score
52.9
#8
51.5
#11
Reasoning
50.3
#12
51.2
#9
Coding
43.0
#7
40.9
#10
Agents
39.0
#8
37.1
#12
Cost, coverage & limits
Benchmark wins
5 of 9
4 of 9
Input price
$0.43 / M
— / M
Output price
$0.87 / M
— / M
Context window
1,048,576
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
DeepSeek-V4-Pro-0813
Hy4 preview
Math
39.9#16
40.2#14
Tool use
33.3#6
32.9#7
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for DeepSeek-V4-Pro-0813 · 32 for Hy4 preview

9 shared

DeepSeek-V4-Pro-0813 outperforms in 5 benchmarks (Agents' Last Exam, CyberGym, Humanity's Last Exam (with tools, text-only), NL2Repo, Terminal-Bench 2.1), while Hy4 preview is better at 3 benchmarks (AutomationBench, DeepSWE, Humanity's Last Exam (no tools, text-only)).

DeepSeek-V4-Pro-0813 has a slight edge in benchmark performance.

Wed Sep 02 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

830.0B diff

DeepSeek-V4-Pro-0813 has 830.0B more parameters than Hy4 preview, making it 107.8% larger.

DeepSeek
DeepSeek-V4-Pro-0813
1.6Tparameters
Tencent
Hy4 preview
770.0Bparameters
1600.0B
DeepSeek-V4-Pro-0813
770.0B
Hy4 preview

Context Window

Maximum input and output token capacity

Only DeepSeek-V4-Pro-0813 specifies input context (1,048,576 tokens). Only DeepSeek-V4-Pro-0813 specifies output context (393,216 tokens).

DeepSeek
DeepSeek-V4-Pro-0813
Input1,048,576 tokens
Output393,216 tokens
Tencent
Hy4 preview
Input- tokens
Output- tokens
Wed Sep 02 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V4-Pro-0813 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-Pro-0813

MIT

Open weights

Hy4 preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V4-Pro-0813 was released on 2026-08-13, while Hy4 preview was released on 2026-08-28.

Hy4 preview is 1 month newer than DeepSeek-V4-Pro-0813.

DeepSeek-V4-Pro-0813

Aug 13, 2026

2 weeks ago

Hy4 preview

Aug 28, 2026

4 days ago

2w 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 DeepSeek-V4-Pro-0813 and Hy4 preview side-by-side, then vote on the output you prefer.

DeepSeek-V4-Pro-0813
✓ Preferred
Hy4 preview
Open in Playground

FAQ

Common questions about DeepSeek-V4-Pro-0813 vs Hy4 preview.

Which is better, DeepSeek-V4-Pro-0813 or Hy4 preview?

DeepSeek-V4-Pro-0813 and Hy4 preview are closely matched on the LLM Stats Score at 52.9 and 51.5. DeepSeek-V4-Pro-0813 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-Pro-0813 compare to Hy4 preview in benchmarks?

DeepSeek-V4-Pro-0813 scores Terminal-Bench 2.1: 87.9%, CyberGym: 83.3%, Toolathlon: 74.1%, DSBench-FullStack: 71.1%, DSBench-Hard: 67.2%. 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-Pro-0813 and Hy4 preview?

DeepSeek-V4-Pro-0813 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-Pro-0813 and Hy4 preview?

Key differences include LLM Stats Score (52.9 vs 51.5), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Pro-0813 and Hy4 preview?

DeepSeek-V4-Pro-0813 is developed by DeepSeek and Hy4 preview is developed by Tencent.

Related comparisons