llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen3 235B A22B

Alibaba Cloud / Qwen Team model product

Qwen3 235B A22B

Qwen3-235B-A22B-Instruct-2507 is the updated instruct version of Qwen3-235B-A22B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It provides substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.

Updated Aug 10, 2026. Default version: Qwen3-235B-A22B-Instruct-2507

Compare
LLMBoard score49.0Qwen3-235B-A22B-Instruct-2507
Coverage80%14 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen3-235B-A22B-Instruct-2507
Released
Jul 22, 2025
Knowledge cutoff
Unknown
Parameters
235B
Context window
262.1K
Max output
16.4K
Inputs
text
Outputs
text
Open weights
Yes
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen3-235B-A22B-Instruct-2507 category scores

Benchmark results

Published benchmark records for the scored version Qwen3-235B-A22B-Instruct-2507.

25 rows
Columns

Show columns

Creative Writing v30.9113100.0%CAug 7, 2026
MultiPL-E0.9113100.0%CAug 7, 2026
CSimpleQA0.82783.3%CAug 7, 2026
ZebraLogic0.93871.4%CAug 7, 2026
Arena-Hard v20.841680.0%CAug 7, 2026
LiveBench 202411250.851469.2%CAug 7, 2026
Multi-IF0.862073.7%CAug 7, 2026
ARC-AGI0.4770.0%CAug 7, 2026
WritingBench0.971557.1%CAug 7, 2026
BFCL-v30.791955.6%CAug 7, 2026
MMLU-ProX0.8113267.7%CAug 7, 2026
SimpleQA0.5114677.8%CAug 7, 2026
Include0.8123163.3%CAug 7, 2026
Aider-Polyglot0.6142238.1%CAug 7, 2026
MMLU-Redux0.9144872.3%CAug 7, 2026
PolyMATH0.5142340.9%CAug 7, 2026
SuperGPQA0.6153457.6%CAug 7, 2026
Tau2 Retail0.7182632.0%CAug 7, 2026
HMMT250.6202520.8%CAug 7, 2026
Tau2 Airline0.423230.0%CAug 7, 2026
IFEval0.9246564.1%CAug 7, 2026
MMLU-Pro0.83112976.6%CAug 7, 2026
LiveCodeBench v60.5455315.4%CAug 7, 2026
AIME 20250.78911422.1%CAug 7, 2026
GPQA0.89623359.0%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

86 rows
Columns

Show columns

text factualitykorean191402.5442N/AAug 6, 2026
text factualitygerman211418.1539N/AAug 6, 2026
text factualityspanish351440.61,087N/AAug 6, 2026
text factualityindustry mathematical421444.82,050N/AAug 6, 2026
text factualitypolish441395.31,053N/AAug 6, 2026
text factualitychinese461486.92,000N/AAug 6, 2026
text factualitymath501438.02,297N/AAug 6, 2026
text factualityexpert531473.62,714N/AAug 6, 2026
text factualityfrench541450.1991N/AAug 6, 2026
text factualityindustry medicine and healthcare541470.62,366N/AAug 6, 2026
textgerman611435.61,707N/AAug 6, 2026
text factualityindustry legal and government621455.42,639N/AAug 6, 2026
textkorean631392.61,720N/AAug 6, 2026
text factualityindustry life and physical and social science651463.06,421N/AAug 6, 2026
textfrench681449.31,980N/AAug 6, 2026
textexpert691443.85,863N/AAug 6, 2026
textindustry mathematical691439.94,902N/AAug 6, 2026
textjapanese691388.91,265N/AAug 6, 2026
text factualitymulti turn711446.97,374N/AAug 6, 2026
text style controlfrench751458.61,980N/AAug 6, 2026
textindustry medicine and healthcare761444.75,686N/AAug 6, 2026
text style controlkorean761384.01,720N/AAug 6, 2026
textlonger query781427.225,604N/AAug 6, 2026
textmulti turn781432.916,961N/AAug 6, 2026
textmath791431.35,887N/AAug 6, 2026
text factualityindustry business and management and financial operations791438.47,736N/AAug 6, 2026
textspanish801424.32,558N/AAug 6, 2026
text factualitylonger query801447.514,022N/AAug 6, 2026
text factualityrussian801428.83,825N/AAug 6, 2026
text style controljapanese811381.81,265N/AAug 6, 2026
text style controlindustry medicine and healthcare821456.15,686N/AAug 6, 2026
textchinese831465.74,938N/AAug 6, 2026
text factualityinstruction following831426.613,191N/AAug 6, 2026
texthard prompts841433.752,023N/AAug 6, 2026
text factualitynon english851419.534,161N/AAug 6, 2026
text style controlgerman851427.81,707N/AAug 6, 2026
textcoding861444.721,199N/AAug 6, 2026
text style controlspanish861422.82,558N/AAug 6, 2026
textindustry software and it services871445.934,559N/AAug 6, 2026
textinstruction following871408.526,840N/AAug 6, 2026
text factualitycoding871478.310,147N/AAug 6, 2026
text factualityindustry writing and literature and language871409.59,474N/AAug 6, 2026
textindustry business and management and financial operations881417.717,875N/AAug 6, 2026
textindustry life and physical and social science881438.415,251N/AAug 6, 2026
textnon english881409.651,832N/AAug 6, 2026
text factualityhard prompts english881461.512,567N/AAug 6, 2026
text style controlmulti turn881437.516,961N/AAug 6, 2026
text style controlindustry business and management and financial operations891431.717,875N/AAug 6, 2026
text factualityhard prompts901453.736,451N/AAug 6, 2026
text factualityindustry entertainment and sports and media901399.37,616N/AAug 6, 2026
text style controlchinese901471.04,938N/AAug 6, 2026
textindustry legal and government911429.66,484N/AAug 6, 2026
texthard prompts english921436.525,452N/AAug 6, 2026
text factualityoverall921431.264,788N/AAug 6, 2026
text factualitycreative writing921398.35,779N/AAug 6, 2026
text style controlhard prompts921447.952,023N/AAug 6, 2026
text style controlnon english921411.351,832N/AAug 6, 2026
text style controlexpert931449.65,863N/AAug 6, 2026
text factualityindustry software and it services941464.819,163N/AAug 6, 2026
textpolish961407.03,810N/AAug 6, 2026
text style controlindustry software and it services961462.934,559N/AAug 6, 2026
text style controlrussian961416.68,378N/AAug 6, 2026
textrussian971410.88,378N/AAug 6, 2026
text factualityexclude ties971425.845,944N/AAug 6, 2026
text style controlindustry legal and government971434.16,484N/AAug 6, 2026
text style controlinstruction following971415.826,840N/AAug 6, 2026
textexclude ties981407.668,887N/AAug 6, 2026
text style controlcoding981472.521,199N/AAug 6, 2026
text style controllonger query981434.725,604N/AAug 6, 2026
text factualityenglish991438.628,958N/AAug 6, 2026
text style controlindustry life and physical and social science991445.715,251N/AAug 6, 2026
text style controlindustry mathematical991430.94,902N/AAug 6, 2026
textoverall1001419.296,721N/AAug 6, 2026
text style controlhard prompts english1021450.725,452N/AAug 6, 2026
text style controloverall1031422.996,721N/AAug 6, 2026
text style controlexclude ties1041414.668,887N/AAug 6, 2026
text style controlmath1051418.25,887N/AAug 6, 2026
text style controlpolish1051403.43,810N/AAug 6, 2026
textenglish1081424.844,824N/AAug 6, 2026
textindustry writing and literature and language1091390.421,553N/AAug 6, 2026
text style controlenglish1111430.244,824N/AAug 6, 2026
textcreative writing1141375.813,473N/AAug 6, 2026
textindustry entertainment and sports and media1141374.617,608N/AAug 6, 2026
text style controlindustry writing and literature and language1141396.821,553N/AAug 6, 2026
text style controlcreative writing1241379.813,473N/AAug 6, 2026
text style controlindustry entertainment and sports and media1241376.917,608N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.069 input, $0.455 output per 1M via Cortecs
Tracked offerings
7
6 rows
Columns

Show columns

Cortecsqwen3-235b-a22b-instruct-2507global$0.069$0.455262KAug 7, 2026
LLM Gatewayqwen3-235b-a22b-instruct-2507global$0.09$0.58262.1KAug 7, 2026
Venice AIqwen3-235b-a22b-instruct-2507global$0.15$0.75128KAug 7, 2026
302.AIqwen3-235b-a22b-instruct-2507global$0.29$1.14128KAug 7, 2026
Scalewayqwen3-235b-a22b-instruct-2507global$0.75$2.25260KAug 7, 2026
GreenPTqwen3-235b-a22b-instruct-2507global$1.03$3.08262.1KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Qwen3 235B A22B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

2 rows
Columns

Show columns

Qwen3-235B-A22B-Instruct-2507Jul 22, 202549.0235B262.1K16.4KYesApache 2.0
Qwen3 235B A22BApr 29, 2025N/A235B131.1K16.4KYesApache 2.0

What is Qwen3 235B A22B?

A concise description based on the published model registry.

Qwen3-235B-A22B-Instruct-2507 is the updated instruct version of Qwen3-235B-A22B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It provides substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen3 235B A22B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen3 235B A22BvsPhi 4 Reasoning PlusQwen3 235B A22BvsNova LiteQwen3 235B A22BvsMistral Small 4Qwen3 235B A22BvsGemini 1.5 ProQwen3 235B A22BvsLlama 4 MaverickQwen3 235B A22BvsMiniMax M1 40K

Models similar to Qwen3 235B A22B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#90-0.9
AC

Qwen3.6 35B A3B

Alibaba Cloud / Qwen Team

48.2 LLMBoard

DetailsCompare
#79+2.5
AC

Qwen2.5 VL 32B

Alibaba Cloud / Qwen Team

51.5 LLMBoard

DetailsCompare
#78+2.7
AC

Qwen3 VL 32B Thinking

Alibaba Cloud / Qwen Team

51.7 LLMBoard

DetailsCompare
#95-3.6
AC

Qwen2.5 Coder 32B

Alibaba Cloud / Qwen Team

45.4 LLMBoard

DetailsCompare
#72+4.0
AC

Qwen2.5 72B

Alibaba Cloud / Qwen Team

53.1 LLMBoard

DetailsCompare
#71+4.2
AC

Qwen3.5 35B A3B

Alibaba Cloud / Qwen Team

53.3 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen3 235B A22B.

When was Qwen3 235B A22B released?

Qwen3 235B A22B's default version was released on Jul 22, 2025.

How much does Qwen3 235B A22B cost?

No official standard PAYG price is currently available for Qwen3 235B A22B. The lowest tracked third-party offer starts at $0.069 input and $0.455 output via Cortecs.

Who created Qwen3 235B A22B?

Qwen3 235B A22B is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen3 235B A22B?

The default version has a 262.1K token context window.

Is Qwen3 235B A22B open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Qwen3 235B A22B?

7 published provider offerings are linked to the default version.

What models should I compare Qwen3 235B A22B with?

Nearby ranked alternatives include Phi 4 Reasoning Plus, Nova Lite, Mistral Small 4.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai