Skip to content
ModelCap

Qwen2.5 Coder 32B Instruct

Current board #87Arena #280Open weights

Qwen·qwen/qwen-2.5-coder-32b-instruct

Qwen2.5 Coder 32B Instruct is a language model published by Qwen. 1 OpenRouter endpoint is published in the latest snapshot. It accepts text input and returns text. The published context limit is 33K tokens.

ModelCap Index · Current board
26.5#87
Measured · 63% support · score interval 26.5–36.5
Market Gravity
15.7
Secondary market signal
Input
$0.66
per 1M tokens
Output
$1.00
per 1M tokens
Context
33K
tokens
Providers
1
endpoint
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Cloudflare$0.66$1.0033K——

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
nscale
live
$0.06$0.20131K572 ms48.6 tok/sstructured
featherless-ai
live
——————

ModelCap Index · Current board

Methodology
26.5
Measured · 3 public benchmark observations across 3 boards
Current board
#87
Public rank basis
Measured (measured)
Index support
62.7% · strong
Index interval
26.5–36.5
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-coder-32b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Qwen/Qwen2.5-Coder-32B-Instruct@381fc969f78efac66bc87ff7ddeadb7e73c218a7 (not the evaluation revision)
Direct benchmark observations
3
Breadth-adjusted BES point estimate
31.5
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
31.5
Evidence status
confirmed · 77% mass
General preference
35.2
Coding
16.8
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
63%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
2.5
Liquidity (providers × uptime)
16.2
Open reach (HF downloads)
65.4
Surface (context / tools / modalities)
15.1
Freshness
8.9
  • · OpenRouter popularity #259
  • · 1 live provider
  • · HF 30d downloads 1138087
  • · Catalogue: context 32768
  • · First seen 2024-11-11

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
89.2
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
89.0
Evaluation provenance
62.7

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
15.7
OpenRouter weekly popularity
#259 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
#280 of 385
Rating
1270.5
95% confidence interval
1262–1279
Votes
5K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
2.5

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
16.2

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

Open reach15%
65.4

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

Freshness5%
8.9

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

Specification

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

Capabilities

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

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
381fc969f78e
Parameters
32.8B
Architecture
Qwen2ForCausalLM
Model type
qwen2
Hugging Face downloads (30d)
1.1M
Downloads (all time)
10.8M
Likes
2K
Repository
Qwen/Qwen2.5-Coder-32B-Instruct
Repository updated
12 Jan 2025, 02:02 UTC
Base lineage
Qwen/Qwen2.5-Coder-32B