All comparisons
HellaSwag 95.7 93.8 HumanEval 85.5 84.8 Massive Multitask Language Understanding 88.5 84.0 LiveCodeBench 49.6 — Aider Polyglot 48.4 — BigCodeBench 50.0 — Chatbot Arena 1302.0 1265.0 MMLU PRO 75.9 69.7 BFCL — 38.4
DeepSeek V3 vs Mistral Large 2
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-12-26 | 2025-11-25 |
| Context window | 64k | 128K |
| Parameters | 671B | 123B |
| Architecture | mixture of experts | decoder only |
| License | Open Source | True |
| Knowledge cutoff | 2024-04 | 2025-07 |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks