Qwen2.5-14B-YOYO-Average: benchmark results

Provider: Alibaba. Access: Open.

Aggregate Rating 1559 ± 35, rank #1562 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - EL59.06Score (%)92.8
Open Japanese LLM - Jcommonsenseqa Exact Match96.07Score (%)92.3
Open Japanese LLM - Jsts Pearson90.25Score (%)88
Open Japanese LLM - Wikicorpus E TO J Comet Wmt2284.24Score (%)85.7
Open Japanese LLM - Jnli Exact Match87.06Score (%)85.1
Open Japanese LLM - Jsts Spearman87.72Score (%)85.1
Open Japanese LLM - MT84.93Score (%)84.6
Open Japanese LLM - Jmmlu Exact Match73Score (%)84.5
Open Japanese LLM - Wiki Dependency SET F139.67Score (%)84.1
Open Japanese LLM - ALT E TO J Comet Wmt2290.92Score (%)82.2
Open Japanese LLM - HE75.58Score (%)82.2
Open Japanese LLM - ALT J TO E Comet Wmt2288.61Score (%)81.7

Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-yoyo-average · How It Works · Data refreshed daily, snapshot 2026-11-08.