Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
deepseek-ai
|
|---|---|
| Company | deepseek-ai |
| Release Date | 2024-07-24 |
| Parameters (B) | 236 |
| Architecture | Mixture-of-Experts |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 640 |
| Compute | 8x NVIDIA A100 80GB (BF16 inference) |
| Benchmark: AGIEval | 60 |
| Benchmark: AIME-2024 | 16.7 |
| Benchmark: ARC | 92.8 |
| Benchmark: Aider | 73.7 |
| Benchmark: BBH | 83.9 |
| Benchmark: C-Eval | 79.4 |
| Benchmark: GSM8K | 94.9 |
| Benchmark: HumanEval | 89.3 |
| Benchmark: LiveCodeBench | 43.4 |
| Benchmark: MATH | 75.7 |
| Benchmark: MBPP | 76.2 |
| Benchmark: MMLU | 79.2 |
| Benchmark: SWE-Bench | 12.7 |
| Pricing (Input) | — |
| Pricing (Output) | — |