DeepSeek model product
DeepSeek-V3.2
2 is a DeepSeek large language model with a specialized variant for specific tasks.
Updated Sep 8, 2026. Default version: DeepSeek-V3.2-Speciale
LLMBoard Score56.6DeepSeek-V3.2-Speciale
Coverage40%8 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
DeepSeek-V3.2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-V3.2 Benchmark Results
Benchmark scores for DeepSeek-V3.2-Speciale.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkHMMT 2025 | Score99.20% | Rank03 | Participants33 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score90.00% | Rank04 | Participants17 | Percentile81.25% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score80.30% | Rank09 | Participants23 | Percentile63.64% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score96.00% | Rank20 | Participants119 | Percentile83.90% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score35.20% | Rank39 | Participants41 | Percentile5.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score46.40% | Rank40 | Participants51 | Percentile22.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score73.10% | Rank50 | Participants113 | Percentile56.25% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score30.60% | Rank52 | Participants103 | Percentile50.00% | EvidenceC | Evaluated |
DeepSeek-V3.2 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.
DeepSeek-V3.2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.58 input, $1.68 output per 1M via Azure Cognitive Services
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAzure Cognitive Services | Provider model IDdeepseek-v3.2-speciale | Regionglobal | Input / 1M$0.58 | Output / 1M$1.68 | Context128K | Updated |
| ProviderAzure | Provider model IDdeepseek-v3.2-speciale | Regionglobal | Input / 1M$0.58 | Output / 1M$1.68 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
DeepSeek-V3.2 Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek-V3.2-Speciale. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepSeek | Output Speed30.00 tok/s | Catalog Latency1.00 s | Max Input131.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
DeepSeek-V3.2 Specifications
Technical details for the model's default version.
- Version
- DeepSeek-V3.2-Speciale
- Released
- Dec 1, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 685B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
DeepSeek-V3.2 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 |
|---|
| VersionDeepSeek-V3.2 | Released | LLMBoardN/A | Parameters685B | Context163.8K | Max output163.8K | Open weightsYes | LicenseMIT |
| VersionDeepSeek-V3.2 (Non-thinking) | Released | LLMBoardN/A | Parameters685B | Context131.1K | Max output8.2K | Open weightsYes | LicenseMIT |
| VersionDeepSeek-V3.2 (Thinking) | Released | LLMBoardN/A | Parameters685B | Context131.1K | Max output65.5K | Open weightsYes | LicenseMIT |
| VersionDeepSeek-V3.2-Speciale | Released | LLMBoard56.64 | Parameters685B | Context131.1K | Max output131.1K | Open weightsNo | LicenseMIT |
| VersionDeepSeek-V3.2-Exp | Released | LLMBoardN/A | Parameters685B | Context163.8K | Max output65.5K | Open weightsYes | LicenseMIT |
Models similar to DeepSeek-V3.2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-R1
DeepSeek
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-V4-Flash
DeepSeek
DE
DeepSeek-V4-Pro
DeepSeek
DE
DeepSeek-V3
DeepSeek
DE
DeepSeek-R1-Distill-Qwen
DeepSeek
What is DeepSeek-V3.2?
Key information about DeepSeek-V3.2 and its available data.
2 is a large language model from DeepSeek. 2-Speciale is a specialized variant optimized for enhanced performance on specific tasks.
Data as of 2026-09-08.
FAQ
Common questions about DeepSeek-V3.2.
When was DeepSeek-V3.2 released?
DeepSeek-V3.2's default version was released on Dec 1, 2025.
How much does DeepSeek-V3.2 cost?
No official standard PAYG price is currently available for DeepSeek-V3.2. The lowest tracked third-party offer starts at $0.58 input and $1.68 output via Azure Cognitive Services.
Who created DeepSeek-V3.2?
DeepSeek-V3.2 was created by DeepSeek.
What is the context window for DeepSeek-V3.2?
The default version has a 131.1K token context window.
Is DeepSeek-V3.2 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer DeepSeek-V3.2?
2 provider offerings are linked to the default version.