modelgrep
Q

Qwen: Qwen3 235B A22B

qwen/qwen3-235b-a22b

119th smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
19.8
119th of 178
Design Elo
1075
Website
Speed
53
160th fastest
Latency
630ms
first token
Input price
$0.455
159th cheapest
Context
131K
8K max out

How it compares

Smarter than33%
of all ranked models
Faster than46%
of all ranked models
Cheaper than47%
of all ranked models

Overview

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Benchmarks

independent · via OpenRouter
Artificial Analysis33th percentile
Intelligence Index
19.8
Coding Index
17.4
Agentic Index
18.4
GPQA Diamond
70%
Humanity's Last Exam
12%
SciCode
40%
Tau²-Bench (agentic)
24%
Design Arena · Elo2,399 tournaments
Website
1075
codecategories
1054
Data Viz
1045
UI Component
1019
Game Dev
998
3D
939

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Alibaba$0.455$1.82100%

Specifications

Context window131K
Max output8K
Knowledge cutoffMar 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 235B A22B FAQ

How much does Qwen3 235B A22B cost?

Qwen3 235B A22B costs $0.455 per million input tokens and $1.82 per million output tokens via OpenRouter, making it 159th cheapest of 298 paid models.

How smart is Qwen3 235B A22B?

Qwen3 235B A22B scores 19.8 on the Artificial Analysis Intelligence Index, ranking 119th of 178 benchmarked models, with a GPQA Diamond score of 70%.

How fast is Qwen3 235B A22B?

Qwen3 235B A22B generates around 53 tokens per second with 630ms time-to-first-token (p50), the 160th fastest tracked model.

What is Qwen3 235B A22B's context window?

Qwen3 235B A22B supports a 131K-token context window and can output up to 8K tokens. It accepts text input.

Compare head-to-head