Claude Haiku 4.5 vs gpt-oss-120b
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Claude Haiku 4.5 | gpt-oss-120b |
|---|---|---|
| Provider |  Anthropic |  OpenAI |
| puntuación promedio | 37.1 | 46.9 |
| Precio de entrada | $1.00 | $0.04 |
| Precio de salida | $5.00 | $0.19 |
| Ventana de contexto | 200K tokens (~100 books) | 131K tokens (~66 books) |
| Publicado el | 2025-10-15 | 2025-08-05 |
| Código abierto | Proprietary | Open Source |
Puntuaciones de benchmark
5 benchmarks · Claude Haiku 4.5: 1, gpt-oss-120b: 4
| Benchmark | Categoría | Claude Haiku 4.5 | gpt-oss-120b |
|---|---|---|---|
| GPQA diamond | knowledge | 61.6 | 67.7 |
| OTIS Mock AIME 2024-2025 | math | 66.6 | 88.9 |
| SimpleQA Verified | knowledge | 5.9 | 13.9 |
| Terminal Bench | coding | 35.5 | 18.7 |
| WeirdML | coding | 45.4 | 48.2 |