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 | 2026-04-22 |
| Parameters (B) | — |
| Architecture | transformers |
| Context Window | 1048576 |
| Input Modalities | text |
| Open Source | Yes |
| License | mit |
| Score | 35 |
| VRAM (GB) | — |
| Compute | |
| Benchmark: AIME-2026 | 95.8 |
| Benchmark: AutomationBench | 37.7 |
| Benchmark: CodeForces | 3289 |
| Benchmark: CyberGym | 38.7 |
| Benchmark: GPQA | 88.1 |
| Benchmark: HLE | 34.8 |
| Benchmark: IFEval | 79.2 |
| Benchmark: IMO-AnswerBench | 88.4 |
| Benchmark: LiveCodeBench | 91.6 |
| Benchmark: MMLU-Pro | 86.4 |
| Benchmark: NL2Repo-Bench | 39.4 |
| Benchmark: SWE-Bench-Multilingual | 73.3 |
| Benchmark: SWE-Bench-Verified | 79 |
| Benchmark: Terminal-Bench-2.0 | 56.9 |
| Benchmark: Terminal-Bench-3.0 | 7.6 |
| Benchmark: Toolathlon-Verified | 49.7 |
| Pricing (Input) | 0.08 |
| Pricing (Output) | 0.16 |