Skip to content
ModelCap

Qwen2.5 VL 72B Instruct

Restricted license

Qwen·qwen/qwen2.5-vl-72b-instruct

Qwen2.5 VL 72B Instruct is a language model published by Qwen. 2 OpenRouter endpoints are published in the latest snapshot. It accepts text, image input and returns text. The published context limit is 128K tokens. The catalogue declares support for structured outputs.

ModelCap Index · Current board
Not scored · 0% support · score interval not available
Market Gravity
32.4
Secondary market signal
Input
$0.25
per 1M tokens
Output
$0.75
per 1M tokens
Context
128K
tokens
Providers
2
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Nebiusfp8Cheapest$0.25$0.7532Kfp8100.0%
Parasailfp8$0.80$1.00128Kfp8

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
ovhcloud
live
$1.01$1.0133K423 ms24.8 tok/sstructured
featherless-ai
live

Reported evaluation leads (34)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
likaixin/ScreenSpot-Pro
overall
53.3
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
android_studio_macos
52.5
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
autocad_windows
26.5
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
blender_windows
43.7
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
davinci_macos
43.2
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
eviews_windows
90
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
excel_macos
56.2
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
fruitloops_windows
35.1
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
illustrator_windows
19.4
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
inventor_windows
42.9
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
linux_common_linux
62
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
macos_common_macos
53.8
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
matlab_macos
66.7
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
origin_windows
32.3
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
photoshop_windows
60.8
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
powerpoint_windows
73.2
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
premiere_windows
40.4
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
pycharm_macos
53.8
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
quartus_windows
31.1
Unpinned
not published
Reported
Quarantined
likaixin/ScreenSpot-Pro
solidworks_windows
40.3
Unpinned
not published
Reported
Quarantined

Showing 20 of 34 rows.

ModelCap Index · Current board

Methodology
Not scored · excessive distance
Public rank basis
Not scored (abstained)
Index support
0.0% · not applicable
Index interval
Not available
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · qwen/qwen/qwen2.5-vl-72b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Qwen/Qwen2.5-VL-72B-Instruct@89c86200743eec961a297729e7990e8f2ddbc4c5 (not the evaluation revision)
Direct benchmark observations
0
Architecture fallback
abstained · 0% coverage · 0 anchors
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
Evidence status
No admitted measured evidence
General preference
Coding
Agents & tools
Reasoning
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
9.4
Liquidity (providers × uptime)
76.4
Open reach (HF downloads)
Surface (context / tools / modalities)
40.0
Freshness
12.2
  • · OpenRouter popularity #174
  • · 2 live providers
  • · Catalogue: context 128000, modalities Text/Image
  • · First seen 2025-02-01

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy
55.1
38.9–71.4 uncertainty interval
Excluded from rank
Confidence
71%
Training support
156 models · 94 lineages
Out-of-domain check
in domain
Feature coverage
86%
Lineage-held-out error
9.1 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
69.5
partial · 76% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
84.9
Evaluation provenance
0.0

Missing: artifactReproducibility.base-lineage, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
32.4
OpenRouter weekly popularity
#174 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Awaiting evaluation

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
9.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
76.4

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
12.2

Time since first public availability, on a six-month half-life.

Specification

Context window
128K tokens
Max output
Inputs
Text, Image
Outputs
Text
Tokenizer
Qwen
Cached input tokens
Not offered
First seen on OpenRouter
1 Feb 2025
Knowledge cutoff
2024-06-30

Capabilities

  • Not supported: Reasoning
  • Not supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
qwen
Pinned revision
89c86200743e
Parameters
73.4B
Architecture
Qwen2_5_VLForConditionalGeneration
Model type
qwen2_5_vl
Hugging Face downloads (30d)
553K
Downloads (all time)
7.3M
Likes
645
Repository updated
6 Jun 2025, 02:48 UTC