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 | 2026-06-27 |
| Parameters (B) | — |
| Architecture | transformers |
| Context Window | — |
| Input Modalities | text |
| Open Source | Yes |
| License | mit |
| Score | 36 |
| VRAM (GB) | — |
| Compute | |
| Benchmark: AIME-2026 | 96.7 |
| Benchmark: AutomationBench | 12.8 |
| Benchmark: BrowseComp | 83.4 |
| Benchmark: CodeForces | 3206 |
| Benchmark: CyberGym | 52.7 |
| Benchmark: IMO-AnswerBench | 89.8 |
| Benchmark: LiveCodeBench | 93.5 |
| Benchmark: MMLU-Pro | 87.5 |
| Benchmark: NL2Repo-Bench | 38.5 |
| Benchmark: SWE-Bench-Multilingual | 76.2 |
| Benchmark: SWE-Bench-Verified | 80.6 |
| Benchmark: Terminal-Bench-2.0 | 67.9 |
| Benchmark: Toolathlon-Verified | 55.9 |
| Pricing (Input) | — |
| Pricing (Output) | — |