All comparisons
Google-Proof Q&A 52.3 — HellaSwag 90.2 — HumanEval 78.4 — Massive Multitask Language Understanding 78.9 — Instruction-Following Evaluation 38.5 — Massive Multi-discipline Multimodal Understanding — 80.7 BFCL — 77.5 SWE-bench Pro — 41.8 MMLU PRO — 88.9
Mistral 7B Instruct v0.3 vs Claude Opus 4.5
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-05-23 | 2025-11-01 |
| Context window | 32K | 200K |
| Parameters | 7B | — |
| Architecture | decoder only | decoder only |
| License | Apache 2.0 | Proprietary |
| Knowledge cutoff | 2023-12 | 2025-12 |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks