Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 236B | 0.5B/1.8B/4B/7B/14B/72B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 32k |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | May 6 2024 | Feb 4 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2vsClaude Haiku 5.5Qwen1.5vsClaude Haiku 5.5DeepSeek V2vsGPT-6.1 SolQwen1.5vsGPT-6.1 SolDeepSeek V2vsGemini 4 ArgonQwen1.5vsGemini 4 ArgonDeepSeek V2vsMuse Spark OpenQwen1.5vsMuse Spark OpenDeepSeek V2vsGrok 4.7Qwen1.5vsGrok 4.7DeepSeek V2vsMistral Large 4Qwen1.5vsMistral Large 4Frequently asked questions
DeepSeek V2 and Qwen1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen1.5 shipped 92 days before DeepSeek V2, so benchmark comparisons should account for the intervening progress.
DeepSeek V2 has 236B parameters, while Qwen1.5 has 0.5B/1.8B/4B/7B/14B/72B. Context windows are 128k (DeepSeek V2) vs 32k (Qwen1.5).
Direct benchmark comparisons are unavailable — DeepSeek V2 and Qwen1.5 don't publish scores on any of the same benchmarks.