Qwen2.5 0.5B Instruct
Open Sourcedi Alibaba · Rilascio 2024-09-16
10.1
punteggio medio
N/A
Prezzo Input
N/A
Prezzo Output
N/A
Finestra di Contesto
text-generation
Tipo
Tested on 6 benchmarks with 10.1% average. Top scores: IFEval (31.5%), MATH Level 5 (10.3%), BBH (HuggingFace) (8.2%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| IFEval | language | 31.5 | |
| MATH Level 5 | math | 10.3 | |
| BBH (HuggingFace) | general | 8.2 | |
| MMLU-PRO | knowledge | 8.0 | |
| MUSR | reasoning | 1.4 | |
| GPQA | knowledge | 1.2 |
Modelli Simili
Google DeepMind
10.4
DeepSeek
10.4
L
Vicuna 7b V1.5LMSYS
10.9
Meta
8.7