Qwen3-235B-A22B

Released
2025-04-29
Last refreshed
2026-06-29
Status
Researched 133d ago
Open sourceCommercial use: permittedCodingRAGLong contextClassificationJSON / Tool use
Alibaba releases · 46 in the last 12 months · this family litChangelog →
Specifications
Family
Qwen3
Released
2025-04-29
Context
128k
Parameters
235B
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Pretrained
Created by
Alibaba

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$0.580
Input / 1M
$0.090

Cheapest of 5 routes · Novita AI

Providers(5)
Fireworks AIAWS BedrockOpenRouterVenice AINovita AI
View 5 provider routes

About

Qwen3-235B-A22B is Alibaba's Qwen3 model. It offers a 128K-token context window.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ B

Provider price ladder

Compare all 5

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.090$0.580
Serverless
AWS Bedrock$0.400$1.20
Serverless
Fireworks AI$1.20$1.20
Serverless
OpenRouter$0.455$1.82
Serverless

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

HumanEvalRank 10 of 97
Claude Sonnet 4.6
98.0
o3
96.7
Claude Opus 4.6
95.0
Grok-3
94.5
Qwen3-235B-A22Bcurrent
92.7
LiveCodeBenchRank 26 of 56
DeepSeek V4 Pro
93.5
Gemini 3.1 Pro Preview
91.7
DeepSeek V4 Flash
91.6
Qwen3.7-Max
91.6
Qwen3-235B-A22Bcurrent
80.4
Aider PolyglotRank 18 of 33
GPT-5
88.0
GPT-5.5
88.0
o3-pro
84.9
Gemini 2.5 Pro
83.1
Qwen3-235B-A22Bcurrent
59.6

Benchmark scores(6)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
HumanEval92.72025-04Observed 2026-04-09—Source
LiveCodeBench80.42026-04Observed 2026-04-14—Source
Aider Polyglot59.62026-04Observed 2026-04-14—Source
Google-Proof Q&A86.1diamondObserved 2026-04-18—Source
MMLU PRO82.8—Observed 2025-04-29—Source
AIME 202485.7—Observed 2025-04-29—Source

Migration checks

No linked migration route is available for this model yet.

Compare Qwen3-235B-A22B with other models

Show all 30 popular comparisonssorted by 7-day search impressions
Qwen3-235B-A22B vs Together AI - Llama 3 8B Lite12Qwen3-235B-A22B vs Llama 3 8B Instruct11Qwen3-235B-A22B vs Llama 3.1 405B Instruct11Qwen3-235B-A22B vs DeepSeek R1 05289Qwen3-235B-A22B vs GLM-5.19Qwen3-235B-A22B vs Kimi K2 Instruct9Qwen3-235B-A22B vs Llama 3.1 70B Instruct8Qwen3-235B-A22B vs GPT-5.56Qwen3-235B-A22B vs Mistral Medium 3.56Qwen3-235B-A22B vs GPT-5.2 Codex5Qwen3-235B-A22B vs Grok-35Qwen3-235B-A22B vs Llama 3 70B Instruct5Qwen3-235B-A22B vs Gemini 2.5 Pro5Qwen3-235B-A22B vs GLM-5V-Turbo4Qwen3-235B-A22B vs Mistral Large 23Qwen3-235B-A22B vs Phi 3.5 Vision Instruct3Qwen3-235B-A22B vs GLM-5 Turbo2Qwen3-235B-A22B vs Claude 3.7 Sonnet1Qwen3-235B-A22B vs Gemini 3 Pro1Qwen3-235B-A22B vs GPT-4o1Qwen3-235B-A22B vs GPT-5.21Qwen3-235B-A22B vs GPT-5.3-Codex-Spark1Qwen3-235B-A22B vs GPT-5.4-Cyber1Qwen3-235B-A22B vs Mistral Large 3 675B Instruct1Qwen3-235B-A22B vs Mixtral 8x22B Instruct v0.31Qwen3-235B-A22B vs Phi-3 Silica1Qwen3-235B-A22B vs Phi 3.5 Mini Instruct1Qwen3-235B-A22B vs GPT-5.5 Instant1Qwen3-235B-A22B vs Llama 3.1 Swallow 70B Instruct1Qwen3-235B-A22B vs o30