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 |
mistralai
|
|---|---|
| Company | mistralai |
| Release Date | 2025-12-02 |
| Parameters (B) | 675 |
| Architecture | Sparse Mixture-of-Experts |
| Context Window | 256000 |
| Input Modalities | text, image |
| Open Source | No |
| License | |
| Score | 9 |
| VRAM (GB) | — |
| Compute | API only |
| Benchmark: AIME-2025 | 38 |
| Benchmark: ARC | 94 |
| Benchmark: Arena-Elo | 1418 |
| Benchmark: Creative-Writing | 1412.2 |
| Benchmark: GPQA-Diamond | 68.4 |
| Benchmark: GSM8K | 93.1 |
| Benchmark: HLE | 4.2 |
| Benchmark: HellaSwag | 93.6 |
| Benchmark: HumanEval | 92 |
| Benchmark: IFEval | 85 |
| Benchmark: LiveCodeBench | 55.3 |
| Benchmark: MATH | 69.1 |
| Benchmark: MATH-500 | 93.6 |
| Benchmark: MMLU | 87.3 |
| Benchmark: MMLU-Pro | 80.7 |
| Benchmark: MMMU-Pro | 66.2 |
| Benchmark: SWE-Bench-Verified | 52.8 |
| Benchmark: SimpleBench | 20.4 |
| Benchmark: SimpleQA | 23.8 |
| Benchmark: Terminal-Bench-2.0 | 9 |
| Benchmark: Terminal-Bench-2.1 | 12 |
| Benchmark: TruthfulQA | 60.5 |
| Pricing (Input) | 0.25 |
| Pricing (Output) | 0.75 |