Model Comparison

DeepSeek VL2 vs Llama 3.2 90B Instruct

DeepSeek VL2 shows notably better performance in the majority of benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

DeepSeek VL2 outperforms in 4 benchmarks (ChartQA, DocVQA, MathVista, TextVQA), while Llama 3.2 90B Instruct is better at 2 benchmarks (AI2D, MMMU).

DeepSeek VL2 shows notably better performance in the majority of benchmarks.

Fri May 01 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Fri May 01 2026 • llm-stats.com
DeepSeek
DeepSeek VL2
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Meta
Llama 3.2 90B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

63.0B diff

Llama 3.2 90B Instruct has 63.0B more parameters than DeepSeek VL2, making it 233.3% larger.

DeepSeek
DeepSeek VL2
27.0Bparameters
Meta
Llama 3.2 90B Instruct
90.0Bparameters
27.0B
DeepSeek VL2
90.0B
Llama 3.2 90B Instruct

Context Window

Maximum input and output token capacity

DeepSeek VL2 accepts 129,280 input tokens compared to Llama 3.2 90B Instruct's 128,000 tokens. DeepSeek VL2 can generate longer responses up to 129,280 tokens, while Llama 3.2 90B Instruct is limited to 128,000 tokens.

DeepSeek
DeepSeek VL2
Input129,280 tokens
Output129,280 tokens
Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Fri May 01 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both DeepSeek VL2 and Llama 3.2 90B Instruct support multimodal inputs.

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

DeepSeek VL2

Text
Images
Audio
Video

Llama 3.2 90B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek VL2 is licensed under deepseek, while Llama 3.2 90B Instruct uses Llama 3.2.

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

DeepSeek VL2

deepseek

Open weights

Llama 3.2 90B Instruct

Llama 3.2

Open weights

Release Timeline

When each model was launched

DeepSeek VL2 was released on 2024-12-13, while Llama 3.2 90B Instruct was released on 2024-09-25.

DeepSeek VL2 is 3 months newer than Llama 3.2 90B Instruct.

DeepSeek VL2

Dec 13, 2024

1.4 years ago

2mo newer
Llama 3.2 90B Instruct

Sep 25, 2024

1.6 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

Provider Availability

DeepSeek VL2 is available from Replicate. Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic.

DeepSeek VL2

replicate logo
Replicate

Llama 3.2 90B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $0.40/1M
bedrock logo
AWS Bedrock
Input Price:Input: $0.72/1MOutput Price:Output: $0.72/1M
fireworks logo
Fireworks
Input Price:Input: $0.89/1MOutput Price:Output: $0.89/1M
together logo
Together
Input Price:Input: $1.20/1MOutput Price:Output: $1.20/1M
hyperbolic logo
Hyperbolic
Input Price:Input: $2.00/1MOutput Price:Output: $2.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Larger context window (129,280 tokens)
Higher ChartQA score (86.0% vs 85.5%)
Higher DocVQA score (93.3% vs 90.1%)
Higher MathVista score (62.8% vs 57.3%)
Higher TextVQA score (84.2% vs 73.5%)
Meta
Higher AI2D score (92.3% vs 81.4%)
Higher MMMU score (60.3% vs 51.1%)

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek VL2
Meta
Llama 3.2 90B Instruct

FAQ

Common questions about DeepSeek VL2 vs Llama 3.2 90B Instruct

DeepSeek VL2 shows notably better performance in the majority of benchmarks. DeepSeek VL2 is made by DeepSeek and Llama 3.2 90B Instruct is made by Meta. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek VL2 scores DocVQA: 93.3%, ChartQA: 86.0%, TextVQA: 84.2%, AI2D: 81.4%, OCRBench: 81.1%. Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%.
DeepSeek VL2 supports 129K tokens and Llama 3.2 90B Instruct supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (129K vs 128K), licensing (deepseek vs Llama 3.2). See the full comparison above for benchmark-by-benchmark results.
DeepSeek VL2 is developed by DeepSeek and Llama 3.2 90B Instruct is developed by Meta.