The AI arena is free today

Open Superagent

DeepSeek-V4-Pro-0813 vs Laguna S 2.1

DeepSeek-V4-Pro-0813 leads the LLM Stats Score 54.1 to 41.4. Laguna S 2.1 is 4.3x cheaper per token.

DeepSeek · Poolside · Updated for 2026

Which is better?

DeepSeek-V4-Pro-0813 leads the overall LLM Stats Score 54.1 to 41.4, ranking #7 overall.

In the 2 individual benchmarks reported for both models, DeepSeek-V4-Pro-0813 wins 2; this is a narrower head-to-head signal than the composite indexes.

On price, Laguna S 2.1 is roughly 4.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose DeepSeek-V4-Pro-0813

  • overall performance matters — it scores 54.1 and ranks #7 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Aug 2026

Choose Laguna S 2.1

  • cost matters — it's about 4.3x cheaper per token

At a glance

The differences that matter most.

DeepSeek-V4-Pro-0813
DeepSeek
Laguna S 2.1
Poolside
Core performance indexes
LLM Stats Score
54.1
#7
41.4
#43
Reasoning
51.5
#8
41.5
#40
Coding
44.2
#7
33.1
#37
Agents
40.4
#7
25.7
#43
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
$0.43 / M
$0.10 / M
Output price
$0.87 / M
$0.20 / M
Context window
1,048,576
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
DeepSeek-V4-Pro-0813
Laguna S 2.1
Tool use
33.6#6
18.9#56
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for DeepSeek-V4-Pro-0813 · 6 for Laguna S 2.1

2 shared

DeepSeek-V4-Pro-0813 outperforms in 2 benchmarks (Terminal-Bench 2.1, Toolathlon), while Laguna S 2.1 is better at 0 benchmarks.

DeepSeek-V4-Pro-0813 significantly outperforms across most benchmarks.

Fri Aug 28 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Laguna S 2.1 costs less

For input processing, DeepSeek-V4-Pro-0813 ($0.43/1M tokens) is 4.3x more expensive than Laguna S 2.1 ($0.10/1M tokens).

For output processing, DeepSeek-V4-Pro-0813 ($0.87/1M tokens) is 4.3x more expensive than Laguna S 2.1 ($0.20/1M tokens).

In conclusion, DeepSeek-V4-Pro-0813 is more expensive than Laguna S 2.1.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Fri Aug 28 2026 • llm-stats.com
DeepSeek
DeepSeek-V4-Pro-0813
Input tokens$0.43
Output tokens$0.87
Best providerDeepSeek
Poolside
Laguna S 2.1
Input tokens$0.10
Output tokens$0.20
Best providerPoolside
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

1482.0B diff

DeepSeek-V4-Pro-0813 has 1482.0B more parameters than Laguna S 2.1, making it 1255.9% larger.

DeepSeek
DeepSeek-V4-Pro-0813
1.6Tparameters
Poolside
Laguna S 2.1
118.0Bparameters
1600.0B
DeepSeek-V4-Pro-0813
118.0B
Laguna S 2.1

Context Window

Maximum input and output token capacity

Both models have the same input context window of 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
Poolside
Laguna S 2.1
Input1,048,576 tokens
Output- tokens
Fri Aug 28 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V4-Pro-0813 is licensed under MIT, while Laguna S 2.1 uses OpenMDW License v1.1.

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

DeepSeek-V4-Pro-0813

MIT

Open weights

Laguna S 2.1

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

DeepSeek-V4-Pro-0813 was released on 2026-08-13, while Laguna S 2.1 was released on 2026-07-21.

DeepSeek-V4-Pro-0813 is 1 month newer than Laguna S 2.1.

DeepSeek-V4-Pro-0813

Aug 13, 2026

2 weeks ago

3w newer
Laguna S 2.1

Jul 21, 2026

1 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

Provider Availability

DeepSeek-V4-Pro-0813 is available from DeepSeek, DeepInfra, Novita, Together. Laguna S 2.1 is available from Poolside.

DeepSeek-V4-Pro-0813

deepseek logo
DeepSeek
Input Price:Input: $0.43/1MOutput Price:Output: $0.87/1M
deepinfra logo
Deepinfra
Input Price:Input: $1.30/1MOutput Price:Output: $2.60/1M
novita logo
Novita
Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M
together logo
Together
Input Price:Input: $1.32/1MOutput Price:Output: $3.96/1M

Laguna S 2.1

poolside logo
Poolside
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M
* 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 DeepSeek-V4-Pro-0813 and Laguna S 2.1 side-by-side, then vote on the output you prefer.

DeepSeek-V4-Pro-0813
✓ Preferred
Laguna S 2.1
Open in Playground

FAQ

Common questions about DeepSeek-V4-Pro-0813 vs Laguna S 2.1.

Which is better, DeepSeek-V4-Pro-0813 or Laguna S 2.1?

DeepSeek-V4-Pro-0813 leads the LLM Stats Score 54.1 to 41.4. DeepSeek-V4-Pro-0813 is made by DeepSeek and Laguna S 2.1 is made by Poolside. 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 Laguna S 2.1 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%. Laguna S 2.1 scores SWE-bench Multilingual: 78.5%, Terminal-Bench 2.1: 70.2%, SWE-Bench Pro: 59.4%, Toolathlon: 49.7%, SWE Atlas - Codebase QnA: 46.2%.

Is DeepSeek-V4-Pro-0813 cheaper than Laguna S 2.1?

Laguna S 2.1 is 4.3x cheaper for input tokens. DeepSeek-V4-Pro-0813 costs $0.43/M input and $0.87/M output via deepseek. Laguna S 2.1 costs $0.10/M input and $0.20/M output via poolside.

What are the context window sizes for DeepSeek-V4-Pro-0813 and Laguna S 2.1?

DeepSeek-V4-Pro-0813 supports 1.0M tokens and Laguna S 2.1 supports 1.0M 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 Laguna S 2.1?

Key differences include LLM Stats Score (54.1 vs 41.4), input pricing ($0.43 vs $0.10/M), licensing (MIT vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Pro-0813 and Laguna S 2.1?

DeepSeek-V4-Pro-0813 is developed by DeepSeek and Laguna S 2.1 is developed by Poolside.

Related comparisons