Qwen2.5 Coder 14B Instruct
Código abiertopor Alibaba · Publicado el 2024-11-06
37.4
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 37.4% average. Top scores: Aider — Code Editing (69.2%), IFEval (69.1%), BBH (HuggingFace) (44.2%).
Puntuaciones de benchmark
| Benchmark | Categoría | Puntuación | Bar |
|---|---|---|---|
| Aider — Code Editing | coding | 69.2 | |
| IFEval | language | 69.1 | |
| BBH (HuggingFace) | general | 44.2 | |
| MMLU-PRO | knowledge | 32.7 | |
| MATH Level 5 | math | 32.5 | |
| GPQA | knowledge | 7.3 | |
| MUSR | reasoning | 7.0 |
Modelos similares
Claude 2Anthropic
37.2
Claude 3.5 HaikuAnthropic
37.2
Mistral NemoMistral AI
37.2
Claude Haiku 4.5Anthropic
37.1