All comparisons
HumanEval 92.9 — SWE-bench Verified 54.6 — Aider Polyglot 52.4 — BFCL 54.0 77.5 MMLU PRO 81.8 88.9 Massive Multi-discipline Multimodal Understanding — 80.7 SWE-bench Pro — 41.8
GPT-4.1 vs Claude Opus 4.5
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2025-04-01 | 2025-11-01 |
| Context window | 1M | 200K |
| Parameters | — | — |
| Architecture | decoder only | decoder only |
| License | Proprietary | Proprietary |
| Knowledge cutoff | 2025-01 | 2025-12 |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks