Qwen3 VL 235B A22B Thinking

Official publisher releaseOpen weights

Qwen3 VL 235B A22B Thinking is a language model from Qwen. Its rank belongs to Qwen3 VL 235B A22B Instruct, the model this route serves. It reads up to 131K tokens of context, and its weights are openly downloadable.

Figures as of 6 Nov 2026, 20:49 UTC · download the public dataset · methodology

ModelCap Index

See primary model · Qwen3 VL 235B A22B Instruct

Route-specific operations remain below

Market Gravity

14.2

Secondary market signal

This separately configured or accelerated route is reviewed as the same underlying model identity as Qwen3 VL 235B A22B Instruct. That canonical product owns rank and capability evidence; pricing, providers and other operational differences remain route-specific below.

Input

Self-hosted

weights only · no listed API price

Output

Self-hosted

weights only · no listed API price

Context

131K

tokens

Providers

endpoints

Providers

Uptime measured over the last 30 minutes

No provider is currently serving this model.

Reported evaluation leads (6)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / task	Metric	Value	Revision	Provenance
MBZUAI/longshot-bench overall	—	47.59	Unpinned `not published`	Reported Quarantined
MBZUAI/longshot-bench core_perception	—	40.5	Unpinned `not published`	Reported Quarantined
MBZUAI/longshot-bench reasoning	—	54.62	Unpinned `not published`	Reported Quarantined
MBZUAI/longshot-bench information	—	46.67	Unpinned `not published`	Reported Quarantined
MBZUAI/longshot-bench multimodal	—	48.56	Unpinned `not published`	Reported Quarantined
TIGER-Lab/MMLU-Pro mmlu_pro	—	83.8	Unpinned `not published`	Reported Quarantined

Deployment readiness

Metadata index

66.1

partial · 74% metadata coverage

Not capability

Artifact reproducibility: 85.0
Access & legal clarity: 100.0
Deployability: 35.0
Evaluation provenance: 50.5

Not yet published: the base model it derives from, a current serving provider, measured provider uptime, published provider pricing, pinned evaluation dataset versions.

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

Market activity

Venue coverage

Market Gravity: 14.2
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.

Market Gravity breakdown

Usage55%: 0.0
Liquidity25%: 0.0
Open reach15%: 87.5
Freshness5%: 21.1

Specification

Model ID: qwen/qwen3-vl-235b-a22b-thinking
Context window: 131K tokens
Declared output cap: 33K tokens
OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
Inputs: Text, Image
Outputs: Text
Tokenizer: Qwen3
Cached input tokens: Not offered
First seen on OpenRouter: 23 Sept 2025
Knowledge cutoff: 2025-03-31

Capabilities

Supported: Reasoning
Supported: Tool use
Supported: Structured output
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: 6664affde684
Parameters: 235.7B
Architecture: Qwen3VLMoeForConditionalGeneration
Model type: qwen3_vl_moe
Hugging Face downloads (30d): 81K
Downloads (all time): 3.6M
Likes: 420
Repository: Qwen/Qwen3-VL-235B-A22B-Thinking
Repository updated: 26 Nov 2025, 13:18 UTC