Qwen2.5 3B Instruct
por Alibaba · Publicado el 2024-09-17
27.2
puntuación promedio
N/A
Precio de entrada
N/A
Precio de salida
N/A
Ventana de contexto
text-generation
Tipo
Tested on 6 benchmarks with 27.2% average. Top scores: IFEval (64.8%), MATH Level 5 (36.8%), BBH (HuggingFace) (25.8%).
Puntuaciones de benchmark
| Benchmark | Categoría | Puntuación | Bar |
|---|---|---|---|
| IFEval | language | 64.8 | |
| MATH Level 5 | math | 36.8 | |
| BBH (HuggingFace) | general | 25.8 | |
| MMLU-PRO | knowledge | 25.1 | |
| MUSR | reasoning | 7.6 | |
| GPQA | knowledge | 3.0 |
Modelos similares
Meta
27.3
Meta
27.4
Microsoft
27.6
DeepSeek
27.8