Qwen3 VL 235B A22B Instruct
by Qwentext+image->text5 endpoints
Neura Intelligence Index
54.7/ 100
Rank
#164—
Confidence
mediumBenchmarks
6(15% coverage)
Overview
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities
Modalities
Input
TextImage
Output
Text
Technical Specifications
Context Window
262.1K tokens
Max Output
32.8K tokens
Knowledge Cutoff
2025-03-31
Tokenizer
Qwen3
Uptime (24h)
9970.6%
Parameters
236000000000B
License
apache_2_0Open Weights
Country
🇨🇳CN
Release Date
September 22, 202512mo
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark Performance
general
| Benchmark | Score | Source |
|---|---|---|
| SimpleQA | 51.9 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 74.7 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU-Pro | 68.1 | verified |
| CharXiv Reasoning | 62.1 | verified |
| ScreenSpot Pro | 62 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| OSWorld | 66.7 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.21
Output$1.90
Cache read$0.10
Added
September 23, 2025
Last synced 9/18/2026