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 |
cohere
|
|---|---|
| Company | cohere |
| Release Date | 2026-05-20 |
| Parameters (B) | 218 |
| Architecture | Sparse Mixture-of-Experts Transformer |
| Context Window | 128000 |
| Input Modalities | text, image |
| Open Source | No |
| License | |
| Score | 13 |
| VRAM (GB) | 160 |
| Compute | 2x NVIDIA H100 80GB (W4A4 recommended) |
| Benchmark: AIME-2025 | 90 |
| Benchmark: AutomationBench | 2 |
| Benchmark: GDPval-AA | 658 |
| Benchmark: GPQA-Diamond | 76.1 |
| Benchmark: HLE | 12 |
| Benchmark: LiveCodeBench | 79.4 |
| Benchmark: MMLU | 79.7 |
| Benchmark: MMLU-Pro | 78.2 |
| Benchmark: MMMU | 75.1 |
| Benchmark: MMMU-Pro | 63 |
| Benchmark: SWE-Bench | 51.8 |
| Benchmark: Terminal-Bench-2.1 | 22.8 |
| Pricing (Input) | 0.30 |
| Pricing (Output) | 1.50 |