Skip to content
ModelCap

Qwen2.5 72B Instruct

Current board #74Arena #257Restricted license

Qwen·qwen/qwen-2.5-72b-instruct

Qwen2.5 72B Instruct is a language model published by Qwen. 2 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 33K tokens. The catalogue declares support for tool use, structured outputs.

ModelCap Index · Current board
38.0#74
Measured · 83% support · score interval 38.0–44.6
Market Gravity
33.3
Secondary market signal
Input
$0.36
per 1M tokens
Output
$0.40
per 1M tokens
Context
33K
tokens
Providers
2
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrafp8Cheapest$0.36$0.4033Kfp899.84%
Novitabf16$0.38$0.4032Kbf16—

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
deepinfra
live
$0.36$0.4033K555 ms30.1 tok/stools · structured
novita
live
$0.38$0.4032K394 ms28.5 tok/stools
featherless-ai
live
——————

ModelCap Index · Current board

Methodology
38.0
Measured · 2 public benchmark observations across 2 boards
Current board
#74
Public rank basis
Measured (measured)
Index support
83.4% · strong
Index interval
38.0–44.6
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/qwen-2.5-72b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Qwen/Qwen2.5-72B-Instruct@495f39366efef23836d0cfae4fbe635880d2be31 (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
41.3
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
41.3
Evidence status
confirmed · 83% mass
General preference
40.3
Coding
45.0
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
83%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
11.6
Liquidity (providers × uptime)
76.3
Open reach (HF downloads)
—
Surface (context / tools / modalities)
35.1
Freshness
7.3
  • · OpenRouter popularity #154
  • · 2 live providers
  • · Catalogue: context 32768, tools
  • · First seen 2024-09-19

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

BES evidence selected · measured input only

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.

Deployment readiness

Metadata index
85.6
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
92.5
Deployability
88.5
Evaluation provenance
52.7

Missing: 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
33.3
OpenRouter weekly popularity
#154 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

Status
Ranked
Source
Arena
Official rank
#257 of 385
Rating
1302.9
95% confidence interval
1299–1307
Votes
39K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
11.6

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
76.3

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%
7.3

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

Specification

Context window
33K tokens
Max output
16K tokens
Inputs
Text
Outputs
Text
Tokenizer
Qwen
Cached input tokens
Not offered
First seen on OpenRouter
19 Sept 2024
Knowledge cutoff
2024-06-30

Capabilities

  • Not supported: Reasoning
  • 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
495f39366efe
Parameters
72.7B
Architecture
Qwen2ForCausalLM
Model type
qwen2
Hugging Face downloads (30d)
427K
Downloads (all time)
8.2M
Likes
970
Repository
Qwen/Qwen2.5-72B-Instruct
Repository updated
12 Jan 2025, 02:07 UTC
Base lineage
Qwen/Qwen2.5-72B