All comparisons
HellaSwag 93.8 — HumanEval 84.8 96.7 Massive Multitask Language Understanding 84.0 — Chatbot Arena 1265.0 1412.0 BFCL 38.4 — MMLU PRO 69.7 — SWE-bench Verified — 71.7 LiveCodeBench — 79.1 Aider Polyglot — 81.3 Google-Proof Q&A — 87.7 Massive Multi-discipline Multimodal Understanding — 82.9
Mistral Large 2 vs o3
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2025-11-25 | 2025-03-31 |
| Context window | 128K | 128K |
| Parameters | 123B | — |
| Architecture | decoder only | decoder only |
| License | True | Unknown |
| Knowledge cutoff | 2025-07 | — |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks