DeepSeek VL2
by DeepSeek
DeepSeek VL2 is a model from DeepSeek, released on December 13, 2024. It has a 129K-token context window and can generate up to 129K output tokens. It ranks #182 of 220 models by Intelligence Score with a score of 2.9.
An advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon 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 specs
| Provider | DeepSeek |
|---|---|
| Release date | 2024-12-13 |
| License | open weights |
| Context window | 129K tokens |
| Max output | 129K tokens |
| Intelligence Score | 2.9 |
Quick answers
What is the context window of DeepSeek VL2?
DeepSeek VL2 has a context window of 129K tokens, with a maximum output of 129K tokens per response.
Is DeepSeek VL2 open source?
Yes. DeepSeek VL2 is an open model released under the open weights license.
When was DeepSeek VL2 released?
DeepSeek released DeepSeek VL2 on December 13, 2024.
How does DeepSeek VL2 compare to Claude Opus 5.5 (Reasoning)?
DeepSeek VL2 scores 2.9 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1.
Compare on the AI leaderboard · All AI models
More models from DeepSeek
- DeepSeek-V4.1-Flash (Reasoning) — DeepSeek
- DeepSeek-V4-Pro-0813 (Reasoning) — DeepSeek
- DeepSeek-V4-Flash-Vision-Exp (Reasoning) — DeepSeek
- DeepSeek-V4-Flash-0423 (Reasoning) — DeepSeek
- DeepSeek-V3.2 (Thinking) (Reasoning) — DeepSeek
- DeepSeek-R1-0528 — DeepSeek