Qwen-14B
Open Sourcevon Alibaba Qwen · Veroeffentlicht 2024-01-01
60.7
Durchschn. Score
N/A
Eingabepreis
N/A
Ausgabepreis
N/A
Kontextfenster
text
Typ
Tested on 7 benchmarks with 60.7% average. Top scores: ARC AI2 (79.2%), LAMBADA (71.1%), GSM8K (61.3%).
Benchmark-Ergebnisse
| Benchmark | Kategorie | Score | Bar |
|---|---|---|---|
| ARC AI2 | knowledge | 79.2 | |
| LAMBADA | knowledge | 71.1 | |
| GSM8K | math | 61.3 | |
| PIQA | knowledge | 59.8 | |
| CMMLU | knowledge | 58.7 | |
| MMLU | knowledge | 55.1 | |
| BBH | reasoning | 40.0 |