DeepSeek model product
DeepSeek-R1-Distill-Qwen
DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token).
Updated Aug 17, 2026. Default version: DeepSeek R1 Distill Qwen 7B
LLMBoard Score14.8DeepSeek R1 Distill Qwen 7B
Coverage60%4 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
DeepSeek-R1-Distill-Qwen Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-R1-Distill-Qwen Benchmark Results
Benchmark scores for DeepSeek R1 Distill Qwen 7B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2024 | Score83.3% | Rank21 | Participants53 | Percentile61.5% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score92.8% | Rank24 | Participants32 | Percentile25.8% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score37.6% | Rank53 | Participants75 | Percentile29.7% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score49.1% | Rank185 | Participants239 | Percentile22.7% | EvidenceC | Evaluated |
DeepSeek-R1-Distill-Qwen 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-R1-Distill-Qwen Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.072 input, $0.144 output per 1M via Alibaba (China)
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba (China) | Provider model IDdeepseek-r1-distill-qwen-7b | Regionglobal | Input / 1M$0.072 | Output / 1M$0.144 | Context32.8K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
DeepSeek-R1-Distill-Qwen Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek R1 Distill Qwen 7B. 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.
DeepSeek-R1-Distill-Qwen Specifications
Technical details for the model's default version.
- Version
- DeepSeek R1 Distill Qwen 7B
- Released
- Jan 20, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 7.6B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
DeepSeek-R1-Distill-Qwen 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 R1 Distill Qwen 1.5B | Released | LLMBoardN/A | Parameters1.8B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
| VersionDeepSeek R1 Distill Qwen 14B | Released | LLMBoardN/A | Parameters14.8B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
| VersionDeepSeek R1 Distill Qwen 32B | Released | LLMBoardN/A | Parameters32.8B | Context131.1K | Max output32.8K | Open weightsYes | LicenseMIT |
| VersionDeepSeek R1 Distill Qwen 7B | Released | LLMBoard14.8 | Parameters7.6B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
DeepSeek-R1-Distill-Qwen vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to DeepSeek-R1-Distill-Qwen
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V2.5
DeepSeek
DE
DeepSeek-R1-Distill-Llama
DeepSeek
DE
DeepSeek-V3
DeepSeek
DE
DeepSeek-VL2
DeepSeek
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-R1
DeepSeek
What is DeepSeek-R1-Distill-Qwen?
Key information about DeepSeek-R1-Distill-Qwen and its available data.
DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning capabilities, delivering strong performance in math, code, and multi-step reasoning tasks.
Data as of 2026-08-17.
FAQ
Common questions about DeepSeek-R1-Distill-Qwen.
When was DeepSeek-R1-Distill-Qwen released?
DeepSeek-R1-Distill-Qwen's default version was released on Jan 20, 2025.
How much does DeepSeek-R1-Distill-Qwen cost?
No official standard PAYG price is currently available for DeepSeek-R1-Distill-Qwen. The lowest tracked third-party offer starts at $0.072 input and $0.144 output via Alibaba (China).
Who created DeepSeek-R1-Distill-Qwen?
DeepSeek-R1-Distill-Qwen was created by DeepSeek.
What is the context window for DeepSeek-R1-Distill-Qwen?
A context window is not available for the default version.
Is DeepSeek-R1-Distill-Qwen open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer DeepSeek-R1-Distill-Qwen?
1 provider offerings are linked to the default version.
What models should I compare DeepSeek-R1-Distill-Qwen with?
Nearby ranked alternatives include Mistral Small 3.2 24B, Mistral Large 3, Gemma 3 27B.