Phi 3 Mini 4k Instruct
Código abiertopor Microsoft · Publicado el 2024-04-22
27.6
puntuación promedio
N/A
Precio de entrada
N/A
Precio de salida
N/A
Ventana de contexto
text-generation
Tipo
Tested on 7 benchmarks with 27.6% average. Top scores: Chatbot Arena Elo — Overall (1127.2%), IFEval (54.8%), BBH (HuggingFace) (36.6%).
Puntuaciones de benchmark
| Benchmark | Categoría | Puntuación | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1127.2 | |
| IFEval | language | 54.8 | |
| BBH (HuggingFace) | general | 36.6 | |
| MMLU-PRO | knowledge | 33.6 | |
| MATH Level 5 | math | 16.4 | |
| MUSR | reasoning | 13.1 | |
| GPQA | knowledge | 11.0 |
Modelos similares
DeepSeek
27.8
Meta
27.4
anthracite-org
27.9
Meta
27.3