Gemma 2 2b It
Código abiertopor Google DeepMind · Publicado el 2024-07-16
36.4
puntuación promedio
N/A
Precio de entrada
N/A
Precio de salida
N/A
Ventana de contexto
text-generation
Tipo
Tested on 12 benchmarks with 36.4% average. Top scores: Chatbot Arena Elo — Overall (1198.5%), JSQuAD (83.8%), JCommonsenseQA (78.2%).
Puntuaciones de benchmark
| Benchmark | Categoría | Puntuación | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1198.5 | |
| JSQuAD | language | 83.8 | |
| JCommonsenseQA | language | 78.2 | |
| JNLI | language | 57.1 | |
| IFEval | language | 56.7 | |
| LLM-JP — Overall | language | 40.5 | |
| JMMLU | language | 38.4 | |
| BBH (HuggingFace) | general | 18.0 | |
| MMLU-PRO | knowledge | 17.2 | |
| MUSR | reasoning | 7.1 | |
| GPQA | knowledge | 3.2 | |
| MATH Level 5 | math | 0.1 |
