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. | 16B | 8B |
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. | 4k | 1M |
| Overview | ||
| Company | DeepSeek | |
| Release date | Jan 11 2024 | Oct 3 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-MoEvsClaude Haiku 5.5Gemini 1.5 Flash-8BvsClaude Haiku 5.5DeepSeek-MoEvsGPT-6.1 SolGemini 1.5 Flash-8BvsGPT-6.1 SolDeepSeek-MoEvsMuse Spark OpenGemini 1.5 Flash-8BvsMuse Spark OpenDeepSeek-MoEvsGrok 4.7Gemini 1.5 Flash-8BvsGrok 4.7DeepSeek-MoEvsMistral Large 4Gemini 1.5 Flash-8BvsMistral Large 4DeepSeek-MoEvsKimi K3Gemini 1.5 Flash-8BvsKimi K3Frequently asked questions
DeepSeek-MoE and Gemini 1.5 Flash-8B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-MoE shipped 266 days before Gemini 1.5 Flash-8B, so benchmark comparisons should account for the intervening progress.
DeepSeek-MoE has 16B parameters, while Gemini 1.5 Flash-8B has 8B. Context windows are 4k (DeepSeek-MoE) vs 1M (Gemini 1.5 Flash-8B). DeepSeek-MoE is open weight, while Gemini 1.5 Flash-8B is closed.
Direct benchmark comparisons are unavailable — DeepSeek-MoE and Gemini 1.5 Flash-8B don't publish scores on any of the same benchmarks.