DeepSeek: DeepSeek-VL2

DeepSeek-VL2 is a mixed-expert (MoE) vision-language model developed based on DeepSeekMoE-27B, employing a sparse-activated MoE architecture to achieve superior performance with only 4.5B active para…

siliconFlow/deepseek-ai/deepseek-vl2

DeepSeek-VL2 is a mixed-expert (MoE) vision-language model developed based on DeepSeekMoE-27B, employing a sparse-activated MoE architecture to achieve superior performance with only 4.5B active parameters. The model excels in various tasks including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Compared to existing open-source dense models and MoE-based models, it demonstrates competitive or state-of-the-art performance using the same or fewer active parameters.

Specifications & capabilities

Input
text, image
Output
text
Max output · tokens
4096
Published model ID
deepseek-vl2
Capabilities
multimodal, structuredOutputs, visionInput

Evaluations

21–40 / 116

MMBench

81.2%

source id
mmBench
leaderboard name
image_style
dimension
vision
metric
image_style
rank
22
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
image_style
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

97.6%

source id
mmBench
leaderboard name
identity_reasoning
dimension
vision
metric
identity_reasoning
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
identity_reasoning
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

71%

source id
mmBench
leaderboard name
physical_property_reasoning
dimension
vision
metric
physical_property_reasoning
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
physical_property_reasoning
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

97.8%

source id
mmBench
leaderboard name
image_topic
dimension
vision
metric
image_topic
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
image_topic
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

93.8%

source id
mmBench
leaderboard name
image_scene
dimension
vision
metric
image_scene
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
image_scene
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

84.1%

source id
mmBench
leaderboard name
Overall
dimension
vision
metric
Overall
rank
32
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
Overall
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
235
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

70.7%

source id
mmBench
leaderboard name
physical_relation
dimension
vision
metric
physical_relation
rank
34
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
physical_relation
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

62.9%

source id
mmBench
leaderboard name
image_quality
dimension
vision
metric
image_quality
rank
35
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
image_quality
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

82%

source id
mmBench
leaderboard name
RR
dimension
vision
metric
RR
rank
36
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
RR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
235
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

84%

source id
mmBench
leaderboard name
AR
dimension
vision
metric
AR
rank
37
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
AR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

82%

source id
mmBench
leaderboard name
CP
dimension
vision
metric
CP
rank
37
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
CP
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

87.3%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
38
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
celebrity_recognition
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

86.7%

source id
mmBench
leaderboard name
attribute_comparison
dimension
vision
metric
attribute_comparison
rank
38
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
attribute_comparison
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

82.4%

source id
mmBench
leaderboard name
Overall
dimension
vision
metric
Overall
rank
38
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
Overall
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

78.1%

source id
mmBench
leaderboard name
FP-C
dimension
vision
metric
FP-C
rank
38
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
FP-C
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

76.9%

source id
mmBench
leaderboard name
object_localization
dimension
vision
metric
object_localization
rank
38
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
object_localization
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

66.3%

source id
mmBench
leaderboard name
structuralized_imagetext_understanding
dimension
vision
metric
structuralized_imagetext_understanding
rank
39
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
structuralized_imagetext_understanding
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

85.9%

source id
mmBench
leaderboard name
social_relation
dimension
vision
metric
social_relation
rank
40
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
social_relation
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

94.8%

source id
mmBench
leaderboard name
ocr
dimension
vision
metric
ocr
rank
41
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
ocr
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

MMBench

55.6%

source id
mmBench
leaderboard name
spatial_relationship
dimension
vision
metric
spatial_relationship
rank
42
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
spatial_relationship
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
DeepSeek-VL2
Original result ↗

Provider specifications & access

1–1 / 1

DeepSeek-VL2 ↗

source model id
deepseek-ai/deepseek-vl2
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
4096
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • structuredOutputs

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

32 / 100

source id
stanfordFMTI
canonical model id
siliconFlow/deepseek-ai/deepseek-vl2
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
DeepSeek
assessment type
organization-level disclosure
metric
disclosure_score
result label
32 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–2 / 2

siliconFlow ↗

field
context_length
value
4K
scope
source-model
source id
siliconFlow
confidence
1

siliconFlow ↗

field
max_output_tokens
value
4K
scope
source-model
source id
siliconFlow
confidence
1

Original sources

1–8 / 8

SiliconFlow · Model page ↗

Hugging Face · Model repository ↗

SiliconFlow · Playground ↗

SiliconFlow · API documentation ↗

GitHub · Catalog ↗

GitHub · Catalog ↗

Hugging Face · Catalog ↗

SiliconFlow · Catalog ↗

Source links

1–4 / 4

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace