modelgrep
Q

Qwen: Qwen3 VL 235B A22B Thinking

qwen/qwen3-vl-235b-a22b-thinking

87th smartest of 178ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
27.6
87th of 178
Design Elo
Speed
44
189th fastest
Latency
1.3s
first token
Input price
$0.260
119th cheapest
Context
131K
33K max out

How it compares

Smarter than51%
of all ranked models
Faster than36%
of all ranked models
Cheaper than60%
of all ranked models

Overview

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

Benchmarks

independent · via OpenRouter
Artificial Analysis49th percentile
Intelligence Index
27.6
Coding Index
20.9
Agentic Index
27.0
GPQA Diamond
77%
Humanity's Last Exam
10%
SciCode
40%
Tau²-Bench (agentic)
54%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Alibaba$0.260$2.6099%
Novitabf16$0.980$3.95

Specifications

Context window131K
Max output33K
Knowledge cutoffMar 2025
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 VL 235B A22B Thinking FAQ

How much does Qwen3 VL 235B A22B Thinking cost?

Qwen3 VL 235B A22B Thinking costs $0.260 per million input tokens and $2.60 per million output tokens via OpenRouter, making it 119th cheapest of 298 paid models.

How smart is Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking scores 27.6 on the Artificial Analysis Intelligence Index, ranking 87th of 178 benchmarked models, with a GPQA Diamond score of 77%.

How fast is Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking generates around 44 tokens per second with 1.3s time-to-first-token (p50), the 189th fastest tracked model.

What is Qwen3 VL 235B A22B Thinking's context window?

Qwen3 VL 235B A22B Thinking supports a 131K-token context window and can output up to 33K tokens. It accepts text, image input.

Compare head-to-head