Alibaba Cloud / Qwen Team model product
Qwen2.5 32B
5 series.
Updated Aug 17, 2026. Default version: Qwen2.5 32B Instruct
LLMBoard Score14.2Qwen2.5 32B Instruct
Coverage80%17 benchmark families
Context windowN/ATokens
Official input price$0.70Alibaba API
Qwen2.5 32B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2.5 32B Benchmark Results
Benchmark scores for Qwen2.5 32B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMMLU-STEM | Score80.9% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMBPP+ | Score67.2% | Rank02 | Participants4 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkTheoremQA | Score44.1% | Rank02 | Participants6 | Percentile80.0% | EvidenceC | Evaluated |
| BenchmarkBBH | Score84.5% | Rank04 | Participants12 | Percentile72.7% | EvidenceC | Evaluated |
| BenchmarkMultiPL-E | Score75.4% | Rank06 | Participants13 | Percentile58.3% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score84.0% | Rank07 | Participants33 | Percentile81.3% | EvidenceC | Evaluated |
| BenchmarkHumanEval+ | Score52.4% | Rank08 | Participants10 | Percentile22.2% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score82.0% | Rank08 | Participants22 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score95.9% | Rank09 | Participants48 | Percentile83.0% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score57.8% | Rank11 | Participants18 | Percentile41.2% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score85.2% | Rank13 | Participants27 | Percentile53.9% | EvidenceC | Evaluated |
| BenchmarkMATH | Score83.1% | Rank15 | Participants71 | Percentile80.0% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score70.4% | Rank22 | Participants34 | Percentile36.4% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.4% | Rank23 | Participants66 | Percentile66.2% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score83.9% | Rank35 | Participants48 | Percentile27.7% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score83.3% | Rank48 | Participants101 | Percentile53.0% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score69.0% | Rank90 | Participants134 | Percentile33.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score49.5% | Rank184 | Participants239 | Percentile23.1% | EvidenceC | Evaluated |
Qwen2.5 32B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Qwen2.5 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
- N/A
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba (China) | Provider model IDqwen2-5-32b-instruct | Regionglobal | Input / 1M$0.287 | Output / 1M$0.861 | Context131.1K | Updated |
| ProviderAlibaba | Provider model IDqwen2-5-32b-instruct | Regionglobal | Input / 1M$0.70 | Output / 1M$2.8 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen2.5 32B Runtime Performance
Provider-specific output speed and catalog latency for Qwen2.5 32B Instruct. 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.
Qwen2.5 32B Specifications
Technical details for the model's default version.
- Version
- Qwen2.5 32B Instruct
- Released
- Sep 19, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 32.5B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Qwen2.5 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 |
|---|
| VersionQwen2.5 32B Instruct | Released | LLMBoard14.2 | Parameters32.5B | ContextN/A | Max outputN/A | Open weightsNo | LicenseApache 2.0 |
Qwen2.5 32B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen2.5 32B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
QvQ 72B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 VL 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 VL 32B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Omni 7B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 4B
Alibaba Cloud / Qwen Team
AC
Qwen2 72B
Alibaba Cloud / Qwen Team
What is Qwen2.5 32B?
Key information about Qwen2.5 32B and its available data.
5 series. , tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities across over 29 languages.
Data as of 2026-08-17.
FAQ
Common questions about Qwen2.5 32B.
When was Qwen2.5 32B released?
Qwen2.5 32B's default version was released on Sep 19, 2024.
How much does Qwen2.5 32B cost?
Qwen2.5 32B's official API price is $0.70 per million input tokens and $2.8 per million output tokens via Alibaba.
Who created Qwen2.5 32B?
Qwen2.5 32B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2.5 32B?
A context window is not available for the default version.
Is Qwen2.5 32B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen2.5 32B?
2 provider offerings are linked to the default version.
What models should I compare Qwen2.5 32B with?
Nearby ranked alternatives include Gemma 3 27B, DeepSeek-R1-Distill-Qwen, QvQ 72B.