Alibaba Cloud / Qwen Team model product
Qwen3 235B A22B
Qwen3 235B A22B is a large language model developed by Alibaba, featuring a Mixture-of-Experts (MoE) architecture with 235 billion total parameters and 22 billion activated parameters.
Updated Aug 17, 2026. Default version: Qwen3-235B-A22B-Instruct-2507
LLMBoard Score41.9Qwen3-235B-A22B-Instruct-2507
Coverage100%25 benchmark families
Context window262.1KTokens
Official input price$0.70Alibaba API
Qwen3 235B A22B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 235B A22B Benchmark Results
Benchmark scores for Qwen3-235B-A22B-Instruct-2507.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCreative Writing v3 | Score87.5% | Rank01 | Participants13 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMultiPL-E | Score87.9% | Rank01 | Participants13 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkCSimpleQA | Score84.3% | Rank02 | Participants8 | Percentile85.7% | EvidenceC | Evaluated |
| BenchmarkZebraLogic | Score95.0% | Rank03 | Participants8 | Percentile71.4% | EvidenceC | Evaluated |
| BenchmarkArena-Hard v2 | Score79.2% | Rank04 | Participants16 | Percentile80.0% | EvidenceC | Evaluated |
| BenchmarkLiveBench 20241125 | Score75.4% | Rank05 | Participants14 | Percentile69.2% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score77.5% | Rank07 | Participants23 | Percentile72.7% | EvidenceC | Evaluated |
| BenchmarkWritingBench | Score85.2% | Rank07 | Participants15 | Percentile57.1% | EvidenceC | Evaluated |
| BenchmarkARC-AGI | Score41.8% | Rank08 | Participants8 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score70.9% | Rank09 | Participants19 | Percentile55.6% | EvidenceC | Evaluated |
| BenchmarkMMLU-ProX | Score79.4% | Rank11 | Participants32 | Percentile67.7% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score54.3% | Rank11 | Participants47 | Percentile78.3% | EvidenceC | Evaluated |
| BenchmarkInclude | Score79.5% | Rank12 | Participants31 | Percentile63.3% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score57.3% | Rank14 | Participants22 | Percentile38.1% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score93.1% | Rank14 | Participants48 | Percentile72.3% | EvidenceC | Evaluated |
| BenchmarkPolyMATH | Score50.2% | Rank14 | Participants23 | Percentile40.9% | EvidenceC | Evaluated |
| BenchmarkSuperGPQA | Score62.6% | Rank15 | Participants34 | Percentile57.6% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score71.3% | Rank18 | Participants26 | Percentile32.0% | EvidenceC | Evaluated |
| BenchmarkHMMT25 | Score55.4% | Rank20 | Participants25 | Percentile20.8% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score44.0% | Rank23 | Participants23 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score88.7% | Rank24 | Participants67 | Percentile65.2% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score83.0% | Rank34 | Participants134 | Percentile75.2% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score51.8% | Rank48 | Participants56 | Percentile14.6% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score70.3% | Rank89 | Participants115 | Percentile22.8% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score77.5% | Rank101 | Participants239 | Percentile58.0% | EvidenceC | Evaluated |
Qwen3 235B A22B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryoverall | Rank93 | Rating / score1431.3 | Votes65,312 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank100 | Rating / score1419.4 | Votes97,477 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank105 | Rating / score1423.0 | Votes97,477 | ObservationsN/A | Result date |
Qwen3 235B A22B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.70 input, $2.8 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.069 input, $0.455 output per 1M via Cortecs
- Tracked offerings
- 21
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderModelScope | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderCortecs | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.069 | Output / 1M$0.455 | Context262K | Updated |
| ProviderMeganova | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.60 | Context262K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.55 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-235b-a22b-2507 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.55 | Context262.1K | Updated |
| ProviderNovitaAI | Provider model IDqwen/qwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.58 | Context131.1K | Updated |
| ProviderLLM Gateway | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.58 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.60 | Context131.1K | Updated |
| ProviderJiekou.AI | Provider model IDqwen/qwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.15 | Output / 1M$0.80 | Context131.1K | Updated |
| ProviderVenice AI | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.15 | Output / 1M$0.75 | Context128K | Updated |
| ProviderNebius Token Factory | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$0.20 | Output / 1M$0.60 | Context262.1K | Updated |
| Providersubmodel | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$0.20 | Output / 1M$0.30 | Context262.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen-3-235b | Regionglobal | Input / 1M$0.22 | Output / 1M$0.88 | Context262.1K | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.23 | Output / 1M$0.92 | Context131.1K | Updated |
| Provider302.AI | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.29 | Output / 1M$1.14 | Context128K | Updated |
| ProviderScaleway | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$0.75 | Output / 1M$2.25 | Context260K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$0.855 | Output / 1M$2.57 | Context262.1K | Updated |
| ProviderGreenPT | Provider model IDqwen3-235b-a22b-instruct-2507 | Regionglobal | Input / 1M$1.03 | Output / 1M$3.08 | Context262.1K | Updated |
| ProviderPioneer | Provider model IDQwen/Qwen3-235B-A22B-Instruct-2507 | Regionglobal | Input / 1M$1.2 | Output / 1M$1.2 | Context262.1K | Updated |
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 Runtime Performance
Provider-specific output speed and catalog latency for Qwen3-235B-A22B-Instruct-2507. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 235B A22B Specifications
Technical details for the model's 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
Qwen3 235B A22B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3-235B-A22B-Instruct-2507 | Released | LLMBoard41.9 | Parameters235B | Context262.1K | Max output16.4K | Open weightsYes | LicenseApache 2.0 |
| VersionQwen3 235B A22B | Released | LLMBoardN/A | Parameters235B | Context131.1K | Max output16.4K | Open weightsYes | LicenseApache 2.0 |
Qwen3 235B A22B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3 235B A22B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 9B
Alibaba Cloud / Qwen Team
AC
Qwen3 Next 80B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 Max
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 32B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
What is Qwen3 235B A22B?
Key information about Qwen3 235B A22B and its available data.
Qwen3 235B A22B is a large language model developed by Alibaba, featuring a Mixture-of-Experts (MoE) architecture with 235 billion total parameters and 22 billion activated parameters.
It achieves competitive results in benchmark evaluations of coding, math, general capabilities, and more, compared to other top-tier models.
Data as of 2026-08-17.
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?
Qwen3 235B A22B's official API price is $0.70 per million input tokens and $2.8 per million output tokens via Alibaba. 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 was created by Alibaba Cloud / Qwen Team.
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?
21 provider offerings are linked to the default version.
What models should I compare Qwen3 235B A22B with?
Nearby ranked alternatives include Step3 VL 10B, Qwen3 VL 235B A22B, Nova 2 Lite.