Devstral 2 2512
Release Date: Dec 9, 2025 Creator: Mistral AI
Devstral 2512 is a powerful code agent model built by Mistral AI for complex software engineering tasks.
| Model Specifications | ||
|---|---|---|
| Knowledge Cutoff | early 2025 | N/A |
| Context (VividLLM) | 32,000 Tokens | N/A Tokens |
| With a context window of 32,000 tokens, this model can 'remember' and analyze up to 48 pages of data at once. This makes it a top choice for reviewing legal contracts and dense academic chapters. | ||
| Context (Native) | 262,144 Tokens | N/A Tokens |
| Input Modalities | TextImagePDF | TextImagePDF |
| Output Type | Text | Text |
| Max Output | 8192 | 8192 |
| Input Weight | 0.50 x (Casual) | N/A |
| Output Weight | 0.50 x (Casual) | N/A |
| Industry Benchmarks | ||
| Intelligence Index (Artificial Analysis) | 22 | N/A |
| Coding Index (Artificial Analysis) | 23.7 | N/A |
| Math Index (Artificial Analysis) | 36.7 | N/A |
| Response Speed | ||
| Output Tokens per second | 64.96 | N/A |
| Median Time to First Token Seconds | 0.72s | N/A |
Launch VividLLM Now => :
Benchmarks accessed via : Artificial Analysis
Disclaimer: We are providing Image Upload options to only limit models as of now, so some models which have image upload options might now have that feature on our site.