Claude Haiku 4.5 vs Gemma 2 9B
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|
| Provider |  Anthropic |  Google DeepMind |
| puntuación promedio | 37.1 | 36.0 |
| Precio de entrada | $1.00 | $0.03 |
| Precio de salida | $5.00 | $0.09 |
| Ventana de contexto | 200K tokens (~100 books) | 8K tokens (~4 books) |
| Publicado el | 2025-10-15 | 2024-06-28 |
| Código abierto | Proprietary | Open Source |
Puntuaciones de benchmark
3 benchmarks · Claude Haiku 4.5: 3, Gemma 2 9B: 0
| Benchmark | Categoría | Claude Haiku 4.5 | Gemma 2 9B |
|---|---|---|---|
| GPQA diamond | knowledge | 61.6 | 3.3 |
| MATH level 5 | math | 96.4 | 21.0 |
| OTIS Mock AIME 2024-2025 | math | 66.6 | 0.5 |