Qwen/Qwen2.5-VL-3B-Instruct

Explore Qwen/Qwen2.5-VL-3B-Instruct: model specifications, capabilities, benchmark results, platform pricing and original sources.

huggingface/Qwen/Qwen2.5-VL-3B-Instruct

Specifications & capabilities

Published model ID
Qwen2.5-VL-3B-Instruct
Capabilities
multimodal, visionInput

Evaluations

1–20 / 116

MMBench

94.9%

source id
mmBench
leaderboard name
social_relation
dimension
vision
metric
social_relation
rank
2
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_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
162
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

92.3%

source id
mmBench
leaderboard name
social_relation
dimension
vision
metric
social_relation
rank
2
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
Qwen2.5-VL-3B
Original result ↗

MMBench

92.4%

source id
mmBench
leaderboard name
image_scene
dimension
vision
metric
image_scene
rank
5
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

96.1%

source id
mmBench
leaderboard name
image_scene
dimension
vision
metric
image_scene
rank
6
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
163
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

93.2%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
8
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
163
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

96.5%

source id
mmBench
leaderboard name
image_topic
dimension
vision
metric
image_topic
rank
11
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
163
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

92.4%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
11
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
Qwen2.5-VL-3B
Original result ↗

MMBench

90.1%

source id
mmBench
leaderboard name
social_relation
dimension
vision
metric
social_relation
rank
12
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

92.5%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
15
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

91%

source id
mmBench
leaderboard name
image_scene
dimension
vision
metric
image_scene
rank
15
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

95.6%

source id
mmBench
leaderboard name
function_reasoning
dimension
vision
metric
function_reasoning
rank
22
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
function_reasoning
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
Qwen2.5-VL-3B
Original result ↗

MMBench

91.8%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
23
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
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
Qwen2.5-VL-3B
Original result ↗

MMBench

83.2%

source id
mmBench
leaderboard name
scenery_building
dimension
vision
metric
scenery_building
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
scenery_building
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
233
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
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
Qwen2.5-VL-3B
Original result ↗

MMBench

89.6%

source id
mmBench
leaderboard name
function_reasoning
dimension
vision
metric
function_reasoning
rank
34
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
function_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
Qwen2.5-VL-3B
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
Qwen2.5-VL-3B
Original result ↗

MMBench

61.9%

source id
mmBench
leaderboard name
cultural_relic
dimension
vision
metric
cultural_relic
rank
42
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
cultural_relic
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
233
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

71.3%

source id
mmBench
leaderboard name
structuralized_imagetext_understanding
dimension
vision
metric
structuralized_imagetext_understanding
rank
45
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_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
162
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

MMBench

97.4%

source id
mmBench
leaderboard name
identity_reasoning
dimension
vision
metric
identity_reasoning
rank
49
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-3B
Original result ↗

Provider specifications & access

1–2 / 2

Qwen/Qwen2.5-VL-3B-Instruct ↗

source model id
HuggingFace/qwen-qwen2.5-vl-3b-instruct@2
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Qwen/Qwen2.5-VL-3B-Instruct ↗

    source model id
    publishers/hf-qwen/models/qwen2.5-vl-3b-instruct@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    26 / 100

    source id
    stanfordFMTI
    canonical model id
    huggingface/Qwen/Qwen2.5-VL-3B-Instruct
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Alibaba
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    26 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–12 / 12

    Hugging Face · Qwen/Qwen2.5-VL-3B-Instruct ↗

    Google Cloud · Model page ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    arXiv · Paper · 2308.12966 ↗

    arXiv · Paper · 2309.00071 ↗

    arXiv · Paper · 2409.12191 ↗

    GitHub · Catalog ↗

    Google Cloud · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–5 / 5

    Hugging Face model card

    1–1 / 1

    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