Alibaba Cloud / Qwen Team model product
Qwen2.5 Coder 32B
5 trillion tokens of code data, supporting 92 programming languages with a 128K context window.
Updated Aug 17, 2026. Default version: Qwen2.5-Coder 32B Instruct
LLMBoard Score4.9Qwen2.5-Coder 32B Instruct
Coverage80%13 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Qwen2.5 Coder 32B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2.5 Coder 32B Benchmark Results
Benchmark scores for Qwen2.5-Coder 32B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBigCodeBench-Full | Score49.6% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkBigCodeBench-Hard | Score27.0% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score90.2% | Rank03 | Participants33 | Percentile93.8% | EvidenceC | Evaluated |
| BenchmarkTheoremQA | Score43.1% | Rank03 | Participants6 | Percentile60.0% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score92.7% | Rank06 | Participants66 | Percentile92.3% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score80.8% | Rank10 | Participants22 | Percentile57.1% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score54.2% | Rank14 | Participants18 | Percentile23.5% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score83.0% | Rank16 | Participants27 | Percentile42.3% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score70.5% | Rank21 | Participants34 | Percentile39.4% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score91.1% | Rank24 | Participants48 | Percentile51.1% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score77.5% | Rank42 | Participants48 | Percentile12.8% | EvidenceC | Evaluated |
| BenchmarkMATH | Score57.2% | Rank51 | Participants71 | Percentile28.6% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score31.4% | Rank62 | Participants75 | Percentile17.6% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score75.1% | Rank77 | Participants101 | Percentile24.0% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score50.4% | Rank119 | Participants134 | Percentile11.3% | EvidenceC | Evaluated |
Qwen2.5 Coder 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 Coder 32B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen2.5 Coder 32B Runtime Performance
Provider-specific output speed and catalog latency for Qwen2.5-Coder 32B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderFireworks | Output Speed110 tok/s | Catalog Latency0.26 s | Max Input128K | Max Output128K | Updated |
| ProviderHyperbolic | Output Speed100 tok/s | Catalog Latency0.5 s | Max Input128K | Max Output128K | Updated |
| ProviderDeepInfra | Output Speed44 tok/s | Catalog Latency0.5 s | Max Input128K | Max Output128K | Updated |
| ProviderLambda | Output Speed42 tok/s | Catalog Latency0.5 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen2.5 Coder 32B Specifications
Technical details for the model's default version.
- Version
- Qwen2.5-Coder 32B Instruct
- Released
- Sep 19, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 32B
- Context window
- 131.1K
- Max output
- 8.2K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen2.5 Coder 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-Coder 32B Instruct | Released | LLMBoard4.9 | Parameters32B | Context131.1K | Max output8.2K | Open weightsYes | LicenseApache 2.0 |
Qwen2.5 Coder 32B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen2.5 Coder 32B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 7B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 2B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 14B
Alibaba Cloud / Qwen Team
AC
Qwen2 72B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 0.8B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Coder 7B
Alibaba Cloud / Qwen Team
What is Qwen2.5 Coder 32B?
Key information about Qwen2.5 Coder 32B and its available data.
5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, repair, and multi-programming tasks while maintaining strong performance in mathematics and general capabilities.
Data as of 2026-08-17.
FAQ
Common questions about Qwen2.5 Coder 32B.
When was Qwen2.5 Coder 32B released?
Qwen2.5 Coder 32B's default version was released on Sep 19, 2024.
How much does Qwen2.5 Coder 32B cost?
No official standard PAYG price is currently available for Qwen2.5 Coder 32B.
Who created Qwen2.5 Coder 32B?
Qwen2.5 Coder 32B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2.5 Coder 32B?
The default version has a 131.1K token context window.
Is Qwen2.5 Coder 32B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen2.5 Coder 32B?
No provider offering is currently linked to the default version.
What models should I compare Qwen2.5 Coder 32B with?
Nearby ranked alternatives include Mistral Large 2, Phi 4 multimodal, Qwen2.5 7B.