The AI arena is free today

Open Superagent

Claude 3.5 Sonnet vs DeepSeek VL2

Claude 3.5 Sonnet leads the LLM Stats Score 19.3 to 3.2.

Anthropic · DeepSeek · Updated for 2026

Which is better?

Claude 3.5 Sonnet leads the overall LLM Stats Score 19.3 to 3.2, ranking #195 overall.

In the 5 individual benchmarks reported for both models, Claude 3.5 Sonnet wins 5; this is a narrower head-to-head signal than the composite indexes.

Claude 3.5 Sonnet also accepts a larger context window (200,000 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 Claude 3.5 Sonnet

  • overall performance matters — it scores 19.3 and ranks #195 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 5 of 5 exact shared results
  • you process long inputs — it offers a 200,000 token context window

Choose DeepSeek VL2

  • you want the most recent training data — it shipped Dec 2024
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
19.3
#195
3.2
#298
20.3
#178
-1.5
#315
Cost, coverage & limits
Benchmark wins
5 of 5
0 of 5
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
129,280

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Claude 3.5 Sonnet
DeepSeek VL2
14.9#86
2.7#162
18.2#69
5.7#132
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

19 reported for Claude 3.5 Sonnet · 14 for DeepSeek VL2

5 shared

Claude 3.5 Sonnet outperforms in 5 benchmarks (AI2D, ChartQA, DocVQA, MathVista, MMMU), while DeepSeek VL2 is better at 0 benchmarks.

Claude 3.5 Sonnet significantly outperforms across most benchmarks.

Thu Sep 03 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Claude 3.5 Sonnet accepts 200,000 input tokens compared to DeepSeek VL2's 129,280 tokens. Claude 3.5 Sonnet can generate longer responses up to 200,000 tokens, while DeepSeek VL2 is limited to 129,280 tokens.

Anthropic
Claude 3.5 Sonnet
Input200,000 tokens
Output200,000 tokens
DeepSeek
DeepSeek VL2
Input129,280 tokens
Output129,280 tokens
Thu Sep 03 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude 3.5 Sonnet and DeepSeek VL2 support multimodal inputs.

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

Claude 3.5 Sonnet

Text
Images
Audio
Video

DeepSeek VL2

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.5 Sonnet is licensed under a proprietary license, while DeepSeek VL2 uses deepseek.

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

Claude 3.5 Sonnet

Proprietary

Closed source

DeepSeek VL2

deepseek

Open weights

Release Timeline

When each model was launched

Claude 3.5 Sonnet was released on 2024-10-22, while DeepSeek VL2 was released on 2024-12-13.

DeepSeek VL2 is 2 months newer than Claude 3.5 Sonnet.

Claude 3.5 Sonnet

Oct 22, 2024

1.9 years ago

DeepSeek VL2

Dec 13, 2024

1.7 years ago

1mo 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

Claude 3.5 Sonnet is available from Anthropic, Bedrock, Google. DeepSeek VL2 is available from Replicate.

Claude 3.5 Sonnet

anthropic logo
Anthropic
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
bedrock logo
AWS Bedrock
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
google logo
Google
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M

DeepSeek VL2

replicate logo
Replicate
* 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 Claude 3.5 Sonnet and DeepSeek VL2 side-by-side, then vote on the output you prefer.

Claude 3.5 Sonnet
✓ Preferred
DeepSeek VL2
Open in Playground

FAQ

Common questions about Claude 3.5 Sonnet vs DeepSeek VL2.

Which is better, Claude 3.5 Sonnet or DeepSeek VL2?

Claude 3.5 Sonnet leads the LLM Stats Score 19.3 to 3.2. Claude 3.5 Sonnet is made by Anthropic and DeepSeek VL2 is made by DeepSeek. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3.5 Sonnet compare to DeepSeek VL2 in benchmarks?

Claude 3.5 Sonnet scores GSM8k: 96.4%, DocVQA: 95.2%, AI2D: 94.7%, HumanEval: 93.7%, BIG-Bench Hard: 93.1%. DeepSeek VL2 scores DocVQA: 93.3%, ChartQA: 86.0%, TextVQA: 84.2%, AI2D: 81.4%, OCRBench: 81.1%.

What are the context window sizes for Claude 3.5 Sonnet and DeepSeek VL2?

Claude 3.5 Sonnet supports 200K tokens and DeepSeek VL2 supports 129K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude 3.5 Sonnet and DeepSeek VL2?

Key differences include LLM Stats Score (19.3 vs 3.2), context window (200K vs 129K), licensing (Proprietary vs deepseek). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.5 Sonnet and DeepSeek VL2?

Claude 3.5 Sonnet is developed by Anthropic and DeepSeek VL2 is developed by DeepSeek.