Qwen: Qwen2.5 VL 72B Instruct

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

qwen/qwen2.5-vl-72b-instruct

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
128000
Knowledge cutoff
2024-06-30
Published model ID
Qwen2.5-VL-72B-Instruct
Capabilities
multimodal, promptCaching, structuredOutputs, visionInput

Evaluations

81–100 / 131

MMBench

73.2%

source id
mmBench
leaderboard name
cultural_relic
dimension
vision
metric
cultural_relic
rank
24
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-72B
Original result ↗

MMBench

71.2%

source id
mmBench
leaderboard name
traditional_show
dimension
vision
metric
traditional_show
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
traditional_show
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-72B
Original result ↗

MMBench

82.2%

source id
mmBench
leaderboard name
image_emotion
dimension
vision
metric
image_emotion
rank
25
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
image_emotion
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-72B
Original result ↗

OpenRouter Benchmarks

44.276%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Nebius
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
25
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Nebius
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-01T12:41:25.955Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.442761
cost_per_task_usd
0.0013494898989898992
output_tokens_per_task
1528.5050505050506
latency_seconds_per_task
69.22869696969697
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
25
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen2.5-vl-72b-instruct
source model id
qwen/qwen2.5-vl-72b-instruct
Original result ↗

MMBench

86.7%

source id
mmBench
leaderboard name
attribute_comparison
dimension
vision
metric
attribute_comparison
rank
26
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
Qwen2.5-VL-72B
Original result ↗

MMBench

81.5%

source id
mmBench
leaderboard name
RR
dimension
vision
metric
RR
rank
26
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
236
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

73.9%

source id
mmBench
leaderboard name
Overall
dimension
vision
metric
Overall
rank
26
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_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
233
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

89.6%

source id
mmBench
leaderboard name
function_reasoning
dimension
vision
metric
function_reasoning
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_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
163
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

86.5%

source id
mmBench
leaderboard name
FP-C
dimension
vision
metric
FP-C
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

77.8%

source id
mmBench
leaderboard name
future_prediction
dimension
vision
metric
future_prediction
rank
28
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
future_prediction
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-72B
Original result ↗

MMBench

82.9%

source id
mmBench
leaderboard name
RR
dimension
vision
metric
RR
rank
29
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
Qwen2.5-VL-72B
Original result ↗

MMBench

84.4%

source id
mmBench
leaderboard name
AR
dimension
vision
metric
AR
rank
31
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
Qwen2.5-VL-72B
Original result ↗

MMBench

82.9%

source id
mmBench
leaderboard name
RR
dimension
vision
metric
RR
rank
32
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

86.7%

source id
mmBench
leaderboard name
sketch_reasoning
dimension
vision
metric
sketch_reasoning
rank
34
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
sketch_reasoning
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-72B
Original result ↗

OpenRouter Benchmarks

45.707%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Parasail
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
34
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Parasail
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-09-01T13:03:42.840Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.457071
cost_per_task_usd
0.0017076717171717172
output_tokens_per_task
1337.1363636363637
latency_seconds_per_task
27.081626262626262
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
36
benchmark_evaluation
true
openrouter_permaslug
qwen/qwen2.5-vl-72b-instruct
source model id
qwen/qwen2.5-vl-72b-instruct
Original result ↗

MMBench

71.9%

source id
mmBench
leaderboard name
calligraphy_painting
dimension
vision
metric
calligraphy_painting
rank
35
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
calligraphy_painting
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-72B
Original result ↗

MMBench

83.7%

source id
mmBench
leaderboard name
image_style
dimension
vision
metric
image_style
rank
36
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_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
295
benchmark_evaluation
true
source model id
Qwen2.5-VL-72B
Original result ↗

MMBench

69%

source id
mmBench
leaderboard name
physical_property_reasoning
dimension
vision
metric
physical_property_reasoning
rank
39
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
Qwen2.5-VL-72B
Original result ↗

MMBench

91.3%

source id
mmBench
leaderboard name
nature_relation
dimension
vision
metric
nature_relation
rank
40
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_Data
verified
Yes
metric_kind
nature_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-72B
Original result ↗

MMBench

93.9%

source id
mmBench
leaderboard name
attribute_recognition
dimension
vision
metric
attribute_recognition
rank
45
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
attribute_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-72B
Original result ↗

Published prices

1–3 / 3

Provider specifications & access

1–3 / 3

Qwen/Qwen2.5-VL-72B-Instruct ↗

source model id
HuggingFace/qwen-qwen2.5-vl-72b-instruct@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Qwen/Qwen2.5-VL-72B-Instruct ↗

    source model id
    publishers/hf-qwen/models/qwen2.5-vl-72b-instruct@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    Qwen2.5-VL-72B-Instruct ↗

    source model id
    Qwen/Qwen2.5-VL-72B-Instruct
    hosting
    siliconflow-hosted
    platforms
    • SiliconFlow
    max output tokens
    4096
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      26 / 100

      source id
      stanfordFMTI
      canonical model id
      qwen/qwen2.5-vl-72b-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

      Source specification observations

      1–5 / 5

      openRouter ↗

      field
      context_length
      value
      128000
      normalized value
      128000
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      context_length
      value
      131K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      openRouter ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2024-06-30
      normalized value
      2024-06-30
      precision
      day
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      115200
      normalized value
      115200
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

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

      Original sources

      1–18 / 18

      SiliconFlow · Model page ↗

      Hugging Face · Model repository ↗

      Google Cloud · Model page ↗

      Microsoft Foundry · Model page ↗

      OpenRouter · Model page ↗

      SiliconFlow · Playground ↗

      Microsoft Foundry · Model documentation ↗

      SiliconFlow · API documentation ↗

      GitHub · Catalog ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      Hugging Face · Catalog ↗

      Hugging Face · Catalog ↗

      LMArena · Catalog ↗

      Microsoft Foundry · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      SiliconFlow · Catalog ↗

      Source links

      1–11 / 11

      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