Qwen2.5 14B Instruct
Open Sourcedi Alibaba · Rilascio 2024-09-16
41.6
punteggio medio
N/A
Prezzo Input
N/A
Prezzo Output
N/A
Finestra di Contesto
text-generation
Tipo
Tested on 6 benchmarks with 41.6% average. Top scores: IFEval (81.4%), MATH Level 5 (55.3%), BBH (HuggingFace) (48.6%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| IFEval | language | 81.4 | |
| MATH Level 5 | math | 55.3 | |
| BBH (HuggingFace) | general | 48.6 | |
| MMLU-PRO | knowledge | 43.2 | |
| MUSR | reasoning | 10.6 | |
| GPQA | knowledge | 10.5 |
Modelli Simili
Mistral AI
41.6
OpenAI
41.5
Anthropic
41.7
Alibaba Qwen
41.3