Claude Haiku 4.5 vs GPT-4.1 Mini
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Claude Haiku 4.5 | GPT-4.1 Mini |
|---|---|---|
| Provider |  Anthropic |  OpenAI |
| puntuación promedio | 37.1 | 44.5 |
| Precio de entrada | $1.00 | $0.40 |
| Precio de salida | $5.00 | $1.60 |
| Ventana de contexto | 200K tokens (~100 books) | 1.0M tokens (~524 books) |
| Publicado el | 2025-10-15 | 2025-04-14 |
| Código abierto | Proprietary | Proprietary |
Puntuaciones de benchmark
7 benchmarks · Claude Haiku 4.5: 7, GPT-4.1 Mini: 0
| Benchmark | Categoría | Claude Haiku 4.5 | GPT-4.1 Mini |
|---|---|---|---|
| ARC-AGI | reasoning | 47.7 | 3.5 |
| ARC-AGI-2 | reasoning | 4.0 | 0.1 |
| FrontierMath-2025-02-28-Private | math | 5.9 | 4.5 |
| GPQA diamond | knowledge | 61.6 | 54.5 |
| MATH level 5 | math | 96.4 | 87.3 |
| OTIS Mock AIME 2024-2025 | math | 66.6 | 44.7 |
| WeirdML | coding | 45.4 | 37.6 |