Alibaba Cloud / Qwen Team model product
Qwen3 32B
8 billion parameters, a 128k token context window, and support for 119 languages.
Updated Oct 23, 2026. Default version: Qwen3 32B
LLMBoard Score29.3Qwen3 32B
Coverage80%8 benchmark families
Context window128KTokens
Official input price$0.70Alibaba API
Qwen3 32B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 32B Benchmark Results
Benchmark scores for Qwen3 32B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMultiLF | Score73.00% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score93.80% | Rank02 | Participants27 | Percentile96.15% | EvidenceC | Evaluated |
| BenchmarkAider | Score50.20% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBFCL | Score70.30% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score65.90% | Rank15 | Participants20 | Percentile26.32% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score74.90% | Rank15 | Participants38 | Percentile62.16% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score81.40% | Rank23 | Participants54 | Percentile58.49% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score65.70% | Rank29 | Participants76 | Percentile62.67% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score73.00% | Rank41 | Participants96 | Percentile57.89% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score36.00% | Rank74 | Participants89 | Percentile17.05% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score72.90% | Rank88 | Participants122 | Percentile28.10% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score0.29% | Rank122 | Participants200 | Percentile39.20% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score36.33% | Rank133 | Participants168 | Percentile20.96% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score7.41% | Rank139 | Participants200 | Percentile30.65% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score66.77% | Rank143 | Participants199 | Percentile28.28% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score17.43% | Rank147 | Participants201 | Percentile27.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,340.12 rating | Rank150 | Participants218 | Percentile31.34% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,346.87 rating | Rank155 | Participants218 | Percentile29.03% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score0.00% | Rank190 | Participants193 | Percentile1.56% | EvidenceB | EvaluatedN/A |
Qwen3 32B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryindustry mathematical | Rank101 | Rating / score1,419.72 | Votes282 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank103 | Rating / score1,425.00 | Votes282 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank118 | Rating / score1,398.56 | Votes316 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank124 | Rating / score1,398.45 | Votes316 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank131 | Rating / score1,341.12 | Votes172 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank135 | Rating / score1,397.97 | Votes236 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank136 | Rating / score1,372.15 | Votes798 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank136 | Rating / score1,368.27 | Votes212 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank137 | Rating / score1,362.20 | Votes236 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank137 | Rating / score1,334.76 | Votes172 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank144 | Rating / score1,406.02 | Votes513 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank144 | Rating / score1,397.59 | Votes843 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank145 | Rating / score1,378.85 | Votes798 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank146 | Rating / score1,379.32 | Votes212 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank148 | Rating / score1,357.01 | Votes187 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank148 | Rating / score1,365.97 | Votes843 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank149 | Rating / score1,367.20 | Votes1,207 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank150 | Rating / score1,296.34 | Votes2,544 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank150 | Rating / score1,340.12 | Votes3,926 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank150 | Rating / score1,381.43 | Votes729 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank151 | Rating / score1,297.08 | Votes616 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank151 | Rating / score1,359.10 | Votes2,230 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank152 | Rating / score1,327.17 | Votes504 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank152 | Rating / score1,316.70 | Votes1,696 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank153 | Rating / score1,355.08 | Votes504 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank154 | Rating / score1,357.47 | Votes513 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank154 | Rating / score1,334.46 | Votes1,207 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank154 | Rating / score1,349.58 | Votes729 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank154 | Rating / score1,318.25 | Votes437 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank155 | Rating / score1,306.68 | Votes2,544 | ObservationsN/A | Result date |
Qwen3 32B 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 $0.08 input, $0.28 output per 1M via Deep Infra
- Tracked offerings
- 19
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProvideriFlow | Provider model IDqwen3-32b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context128K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3-32B | Regionglobal | Input / 1M$0.08 | Output / 1M$0.28 | Context41K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-32b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.28 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3-32b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.28 | Context41K | Updated |
| ProviderAbacus | Provider model IDQwen/Qwen3-32B | Regionglobal | Input / 1M$0.08 | Output / 1M$0.28 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDqwen/qwen3-32b | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context41K | Updated |
| ProviderJiekou.AI | Provider model IDqwen/qwen3-32b-fp8 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.45 | Context41K | Updated |
| ProviderAmazon Bedrock | Provider model IDqwen.qwen3-32b-v1:0 | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context32.8K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-32b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context131.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen-3-32b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context128K | Updated |
| ProviderCortecs | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.179 | Output / 1M$0.697 | Context16.4K | Updated |
| ProviderDigitalOcean | Provider model IDalibaba-qwen3-32b | Regionglobal | Input / 1M$0.25 | Output / 1M$0.55 | Context32.8K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.287 | Output / 1M$1.15 | Context131.1K | Updated |
| ProviderQiniu | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.2899 | Output / 1M$1.16 | Context40K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-32B | Regionglobal | Input / 1M$0.29 | Output / 1M$0.59 | Context131.1K | Updated |
| ProviderHelicone | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.29 | Output / 1M$0.59 | Context131.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.36 | Output / 1M$0.87 | Context41K | Updated |
| ProviderAlibaba | Provider model IDqwen3-32b | Regionglobal | Input / 1M$0.70 | Output / 1M$2.8 | Context131.1K | Updated |
| ProviderPioneer | Provider model IDQwen/Qwen3-32B | Regionglobal | Input / 1M$0.90 | Output / 1M$0.90 | Context131.1K | Updated |
Qwen3 32B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 32B. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderSambanova | Output Speed327.70 tok/s | Catalog Latency1.08 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 32B Specifications
Technical details for the model's default version.
- Version
- Qwen3 32B
- Released
- Apr 29, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 32.8B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 32B 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 32B | Released | LLMBoard29.34 | Parameters32.8B | Context128K | Max output128K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3 32B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3.5 4B
Alibaba Cloud / Qwen Team
AC
Qwen3 14B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B Thinking
Alibaba Cloud / Qwen Team
What is Qwen3 32B?
Key information about Qwen3 32B and its available data.
Qwen3 32B is a large language model in Alibaba's Qwen3 series. It supports hybrid thinking modes for switching between deep reasoning and fast responses, with capabilities in reasoning, instruction-following, and agent tasks.
Data as of 2026-10-22.
FAQ
Common questions about Qwen3 32B.
When was Qwen3 32B released?
Qwen3 32B's default version was released on Apr 29, 2025.
How much does Qwen3 32B cost?
Qwen3 32B'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 $0.08 input and $0.28 output via Deep Infra.
Who created Qwen3 32B?
Qwen3 32B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 32B?
The default version has a 128K token context window.
Is Qwen3 32B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3 32B?
19 provider offerings are linked to the default version.