The AI arena is free today

Open Superagent

Claude 3.7 Sonnet vs DeepSeek VL2 Tiny

Claude 3.7 Sonnet leads the LLM Stats Score 23.9 to -4.7.

Anthropic · DeepSeek · Updated for 2026

Which is better?

Claude 3.7 Sonnet leads the overall LLM Stats Score 23.9 to -4.7, ranking #169 overall.

In the 1 individual benchmarks reported for both models, Claude 3.7 Sonnet 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 Claude 3.7 Sonnet

  • overall performance matters — it scores 23.9 and ranks #169 on LLM Stats
  • your work emphasizes reasoning — 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 Feb 2025

Choose DeepSeek VL2 Tiny

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Claude 3.7 Sonnet
Anthropic
DeepSeek VL2 Tiny
DeepSeek
Core performance indexes
LLM Stats Score
23.9
#169
-4.7
#351
Reasoning
23.1
#165
-12.7
#362
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
—

Individual benchmarks

11 reported for Claude 3.7 Sonnet · 14 for DeepSeek VL2 Tiny

1 shared

Claude 3.7 Sonnet outperforms in 1 benchmarks (MMMU), while DeepSeek VL2 Tiny is better at 0 benchmarks.

Claude 3.7 Sonnet significantly outperforms across most benchmarks.

Thu Sep 17 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
DeepSeek
DeepSeek VL2 Tiny
Input- tokens
Output- tokens
Thu Sep 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude 3.7 Sonnet and DeepSeek VL2 Tiny support multimodal inputs.

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

Claude 3.7 Sonnet

Text
Images
Audio
Video

DeepSeek VL2 Tiny

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.7 Sonnet is licensed under a proprietary license, while DeepSeek VL2 Tiny uses deepseek.

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

Claude 3.7 Sonnet

Proprietary

Closed source

DeepSeek VL2 Tiny

deepseek

Open weights

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while DeepSeek VL2 Tiny was released on 2024-12-13.

Claude 3.7 Sonnet is 2 months newer than DeepSeek VL2 Tiny.

Claude 3.7 Sonnet

Feb 24, 2025

1.6 years ago

2mo newer
DeepSeek VL2 Tiny

Dec 13, 2024

1.8 years 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 Claude 3.7 Sonnet and DeepSeek VL2 Tiny side-by-side, then vote on the output you prefer.

Claude 3.7 Sonnet
✓ Preferred
DeepSeek VL2 Tiny
Open in Playground

FAQ

Common questions about Claude 3.7 Sonnet vs DeepSeek VL2 Tiny.

Which is better, Claude 3.7 Sonnet or DeepSeek VL2 Tiny?

Claude 3.7 Sonnet leads the LLM Stats Score 23.9 to -4.7. Claude 3.7 Sonnet is made by Anthropic and DeepSeek VL2 Tiny 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 3.7 Sonnet compare to DeepSeek VL2 Tiny in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. DeepSeek VL2 Tiny scores DocVQA: 88.9%, ChartQA: 81.0%, OCRBench: 80.9%, TextVQA: 80.7%, AI2D: 71.6%.

What are the context window sizes for Claude 3.7 Sonnet and DeepSeek VL2 Tiny?

Claude 3.7 Sonnet supports 200K tokens and DeepSeek VL2 Tiny 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 Claude 3.7 Sonnet and DeepSeek VL2 Tiny?

Key differences include LLM Stats Score (23.9 vs -4.7), licensing (Proprietary vs deepseek). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and DeepSeek VL2 Tiny?

Claude 3.7 Sonnet is developed by Anthropic and DeepSeek VL2 Tiny is developed by DeepSeek.

Related comparisons