Model Comparison

DeepSeek VL2 Small vs DeepSeek VL2 Tiny

DeepSeek VL2 Small significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

14 benchmarks

DeepSeek VL2 Small outperforms in 14 benchmarks (AI2D, ChartQA, DocVQA, InfoVQA, MathVista, MMBench, MMBench-V1.1, MME, MMMU, MMStar, MMT-Bench, OCRBench, RealWorldQA, TextVQA), while DeepSeek VL2 Tiny is better at 0 benchmarks.

DeepSeek VL2 Small significantly outperforms across most benchmarks.

Wed May 13 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

13.0B diff

DeepSeek VL2 Small has 13.0B more parameters than DeepSeek VL2 Tiny, making it 433.3% larger.

DeepSeek
DeepSeek VL2 Small
16.0Bparameters
DeepSeek
DeepSeek VL2 Tiny
3.0Bparameters
16.0B
DeepSeek VL2 Small
3.0B
DeepSeek VL2 Tiny

Input Capabilities

Supported data types and modalities

Both DeepSeek VL2 Small and DeepSeek VL2 Tiny support multimodal inputs.

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

DeepSeek VL2 Small

Text
Images
Audio
Video

DeepSeek VL2 Tiny

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under deepseek.

Both models share the same licensing terms, providing consistent usage rights.

DeepSeek VL2 Small

deepseek

Open weights

DeepSeek VL2 Tiny

deepseek

Open weights

Release Timeline

When each model was launched

Both models were released on 2024-12-13.

They likely represent similar generations of model development.

DeepSeek VL2 Small

Dec 13, 2024

1.4 years ago

DeepSeek VL2 Tiny

Dec 13, 2024

1.4 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→

Key Takeaways

DeepSeek
Higher AI2D score (80.0% vs 71.6%)
Higher ChartQA score (84.5% vs 81.0%)
Higher DocVQA score (92.3% vs 88.9%)
Higher InfoVQA score (75.8% vs 66.1%)
Higher MathVista score (60.7% vs 53.6%)
Higher MMBench score (80.3% vs 69.2%)
Higher MMBench-V1.1 score (79.3% vs 68.3%)
Higher MME score (21.2% vs 19.1%)
Higher MMMU score (48.0% vs 40.7%)
Higher MMStar score (57.0% vs 45.9%)
Higher MMT-Bench score (62.9% vs 53.2%)
Higher OCRBench score (83.4% vs 80.9%)
Higher RealWorldQA score (65.4% vs 64.2%)
Higher TextVQA score (83.4% vs 80.7%)
DeepSeek

No standout differentiators in the data we have for this pair.

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek VL2 Small
DeepSeek
DeepSeek VL2 Tiny

FAQ

Common questions about DeepSeek VL2 Small vs DeepSeek VL2 Tiny.

Which is better, DeepSeek VL2 Small or DeepSeek VL2 Tiny?

DeepSeek VL2 Small significantly outperforms across most benchmarks. DeepSeek VL2 Small is made by DeepSeek and DeepSeek VL2 Tiny is made by DeepSeek. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does DeepSeek VL2 Small compare to DeepSeek VL2 Tiny in benchmarks?

DeepSeek VL2 Small scores DocVQA: 92.3%, ChartQA: 84.5%, OCRBench: 83.4%, TextVQA: 83.4%, MMBench: 80.3%. DeepSeek VL2 Tiny scores DocVQA: 88.9%, ChartQA: 81.0%, OCRBench: 80.9%, TextVQA: 80.7%, AI2D: 71.6%.