Qwen2 0.5B Instruct vs Gpt2 Large
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Qwen2 0.5B Instruct | Gpt2 Large |
|---|---|---|
| Provider |  Alibaba |  OpenAI |
| puntuación promedio | 6.6 | 5.6 |
| Precio de entrada | - | - |
| Precio de salida | - | - |
| Ventana de contexto | - | - |
| Publicado el | 2024-06-03 | 2022-03-02 |
| Código abierto | Open Source | Open Source |
Puntuaciones de benchmark
6 benchmarks · Qwen2 0.5B Instruct: 4, Gpt2 Large: 2
| Benchmark | Categoría | Qwen2 0.5B Instruct | Gpt2 Large |
|---|---|---|---|
| BBH (HuggingFace) | general | 5.9 | 3.3 |
| GPQA | knowledge | 0.0 | 1.2 |
| IFEval | language | 22.5 | 20.5 |
| MATH Level 5 | math | 2.9 | 1.2 |
| MMLU-PRO | knowledge | 5.9 | 1.6 |
| MUSR | reasoning | 2.4 | 5.7 |