MultimodalOpen weights

Qwen3 VL 235B A22B Instruct

Alibaba

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: Multimodal
Access: Open weights
Released: September 23, 2025
Context window: 262,144 tokens
Knowledge cutoff: March 31, 2025
Output speed: 51 tok/s
Latency (TTFT): 1.2s
Input: Text, Image
Output: Text
API pricing: $0.20 in · $0.88 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

71.2

Coding

59.4

Math

70.7

General

MMLU-Pro	82.3
Humanity’s Last Exam	6.3

Compare Qwen3 VL 235B A22B Instruct with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Qwen3 VL 235B A22B Instruct alternatives →