Skip to content
ModelCap

SWE Dev 32B

Current board #184Official publisher releaseOpen weights7d #185 → #184

Zai Org·zai-org/SWE-Dev-32B

SWE Dev 32B is ModelCap current-board rank #184 with Index 14.7 (Modeled · lineage), from the ModelCap Index as of 15 Sept 2026, 19:09 UTC.

SWE Dev 32B weight access is open weights, from ModelCap classification of published repository metadata as of 15 Sept 2026, 19:09 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
14.7#184
Inherited · 25% support · score interval 0.0–31.6
No admitted evaluation publication timestamp yet
Market Gravity
7.2
Secondary market signal

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
Self-hosted
weights only · no listed API price
Output
Self-hosted
weights only · no listed API price
Context
tokens
Providers
0
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

ModelCap Index · Current board

Methodology
14.7
Modeled · lineage · finetune of qwen/qwen-2.5-coder-32b-instruct · finetune (100%)
Current board
#184
Public rank basis
Modeled · lineage (lineage)
Index support
24.6% · limited
Index interval
0.0–31.6
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
No admitted evaluation publication timestamp
Identity binding
Exact catalogue product · zai-org/zai-org/SWE-Dev-32B · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/SWE-Dev-32B@6f8669b846e9e879a48460b33944ebf4ac6bee57 (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
14.7
Verified lineage
qwen/qwen-2.5-coder-32b-instruct · minus 1.2 ( finetune)
How this position was produced · fused launch placement

No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.

Fused estimate
14.7 ± 13.2
Independent share
0%
Shrink toward corpus
0.0
Optimism haircut
None applied
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Verified lineage · not independent
finetune of qwen/qwen-2.5-coder-32b-instruct · finetune
14.7 ± 13.2100%
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)
Liquidity (providers × uptime)
Open reach (HF downloads)
43.7
Surface (context / tools / modalities)
0.0
Freshness
13.4
  • · HF 30d downloads 317
  • · Catalogue surface
  • · First seen 2025-04-06

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
31.4
12.1–50.6 uncertainty interval
Excluded from rank
Confidence
69%
Training support
180 models · 103 lineages
Out-of-domain check
in domain
Feature coverage
71%
Lineage-held-out error
10.3 MAE

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

Deployment readiness

Metadata index
52.4
partial · 56% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
0.0

Missing: deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, deployability.declared-capacity, 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
7.2
OpenRouter weekly popularity
Not listed

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

No matched Arena rating

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%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

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

Open reach15%
43.7

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

Freshness5%
13.4

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

Specification

Context window
tokens
Max output
Inputs
Text
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
6 Apr 2025

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
mit
Pinned revision
6f8669b846e9
Parameters
32.8B
Architecture
Qwen2ForCausalLM
Model type
qwen2
Hugging Face downloads (30d)
317
Downloads (all time)
2K
Likes
30
Repository updated
9 Jul 2025, 03:45 UTC

Compare SWE Dev 32B with

Pick any model

Alternatives to SWE Dev 32B, by the numbers

Ranked neighbours

Models within 3 places of #184 on the ModelCap Index.

SWE Dev 32B: common questions

How does SWE Dev 32B rank among AI models?

SWE Dev 32B holds ModelCap Index position #184 of 203 ranked language models as of 15 September 2026, with an Index score of 14.7 (interval 0.0–31.6); evidence: modeled · lineage. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does SWE Dev 32B cost per 1M tokens?

No live API price is listed for SWE Dev 32B in the current snapshot as of 15 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is SWE Dev 32B open-weight?

Open weights (mit). 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. The repository is zai-org/SWE-Dev-32B on Hugging Face.

Which benchmarks has SWE Dev 32B been evaluated on?

SWE Dev 32B's Index position rests on the evidence listed on this page; it has no result on the public boards ModelCap tracks as separate leaderboards as of 15 September 2026. The evidence panel names each source and its publication date.

How does SWE Dev 32B compare with Arcee Blitz?

SWE Dev 32B ranks #184 (Index 14.7) and Arcee Blitz ranks #185 (Index 14.4) on the ModelCap Index as of 15 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was SWE Dev 32B released?

SWE Dev 32B first appeared in the catalogue on 6 Apr 2025. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.