DeepSeek VL2 Tiny
MultimodalAn advanced series of large multimodal Mixture-of-Experts (MoE) Vision-Language models that significantly surpasses its predecessor DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding.
Key Specifications
Parameters
3.0B
Context
-
Release Date
December 13, 2024
Average Score
63.1%
Timeline
Key dates in the model's history
Announcement
December 13, 2024
Last Update
July 19, 2025
Today
March 25, 2026
Technical Specifications
Parameters
3.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Benchmark Results
Model performance metrics across various tests and benchmarks
Multimodal
Working with images and visual data
AI2D
test • Self-reported
ChartQA
test • Self-reported
DocVQA
test • Self-reported
MathVista
testmini • Self-reported
MMMU
AI: val val • Self-reported
Other Tests
Specialized benchmarks
InfoVQA
test • Self-reported
MMBench
test • Self-reported
MMBench-V1.1
cn test • Self-reported
MME
Standard evaluation AI: methods formation for solutions. should be exclusively and on context • Self-reported
MMStar
Standard evaluation
AI: (GPT-4o/Claude/etc.) • Self-reported
MMT-Bench
Standard evaluation
AI: The magic bullet is a model's ability to solve most questions in a benchmark given one try, or more generally, to solve many questions in one go. • Self-reported
OCRBench
Standard Evaluation Standard evaluation AI: need to evaluate problem and solution. I and her/its solve, on data and mathematical • Self-reported
RealWorldQA
Standard evaluation AI: Translation descriptions model artificial intelligence on Russian language - standard evaluation performance and capabilities • Self-reported
TextVQA
In deep training and machine training, relates to to evaluation and testing models for verification their efficiency and to This not simply verification accuracy, but also evaluation abilities model data, which she/it not and her/its in real conditions. includes in itself: 1. set data for not at training 2. various scores efficiency 3. on and 4. 5. on to examples 6. Analysis cases, when model gives incorrect In LLM often includes also evaluation by such how: - Accuracy information - and answers - to in various tasks - Quality reasoning helps that model to and that in her can improvements on basis • Self-reported
License & Metadata
License
deepseek
Announcement Date
December 13, 2024
Last Updated
July 19, 2025
Similar Models
All ModelsDeepSeek VL2
DeepSeek
MM27.0B
Released:Dec 2024
Price:$9.50/1M tokens
DeepSeek VL2 Small
DeepSeek
MM16.0B
Released:Dec 2024
DeepSeek R1 Distill Qwen 1.5B
DeepSeek
1.8B
Best score:0.3 (GPQA)
Released:Jan 2025
DeepSeek R1 Distill Qwen 7B
DeepSeek
7.6B
Best score:0.5 (GPQA)
Released:Jan 2025
DeepSeek R1 Distill Llama 8B
DeepSeek
8.0B
Best score:0.5 (GPQA)
Released:Jan 2025
Phi-3.5-vision-instruct
Microsoft
MM4.2B
Released:Aug 2024
Granite 3.3 8B Base
IBM
MM8.2B
Best score:0.9 (HumanEval)
Released:Apr 2025
Gemma 3 4B
MM4.0B
Best score:0.7 (HumanEval)
Released:Mar 2025
Price:$0.02/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.