DeepSeek is a Chinese open-weight model family known for cost-efficient Mixture-of-Experts architectures. DeepSeek V3 and the R1 reasoning model match or exceed closed frontier models on coding and math at a fraction of the inference cost.
See all models from DeepSeekModels in family
6
Open weight
6
API only
0
Avg score
59.8
Top benchmark
98.3
MATH-500
Total HF downloads
14.5M
Primary modality
Text
Context window
128K – 1.0M
First release
Dec 2024
Latest release
Apr 2026
Every release in the DeepSeek family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB66.6 | 671B | Jan 2025 | |
| 2 | text | BB63.6 | 284B | Apr 2026 | |
| 3 | text | BB62.2 | 1.6T | Apr 2026 | |
| 4 | text | BB58.4 | 685B | Nov 2025 | |
| 5 | text | BB57.7 | 671B | Dec 2024 | |
| 6 | text | CC50.6 | 671B | Jul 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Apr 24
Apr 24
Nov 30
Jul 31
Jan 19
Dec 25
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB66.6 | 671B | Jan 2025 | |
| 2 | text | BB63.6 | 284B | Apr 2026 | |
| 3 | text | BB62.2 | 1.6T | Apr 2026 | |
| 4 | text | BB58.4 | 685B | Nov 2025 | |
| 5 | text | BB57.7 | 671B | Dec 2024 | |
| 6 | text | CC50.6 | 671B | Jul 2025 |
The DeepSeek family is a series of AI models from DeepSeek. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, DeepSeek-R1 is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.
