Qwen2.5-7B-o1-ja-v0.1: benchmark results

Provider: Alibaba. Access: Open.

Aggregate Rating 1504 ± 35, rank #2278 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Jsick Exact Match83.48Score (%)84.4
Open Japanese LLM - Xlsum JA Rouge130.59Score (%)83.9
Open Japanese LLM - Xlsum JA RougeLsum25.35Score (%)80.5
Open Japanese LLM - Xlsum JA Bert Score JA F169.62Score (%)65.3
Open Japanese LLM - SUM10.22Score (%)63.6
Open Japanese LLM - Xlsum JA Rouge210.22Score (%)63.6
Open Japanese LLM - Wiki NER SET F17.08Score (%)62.7
Open Japanese LLM - Wiki Dependency SET F136.04Score (%)61.5
Open Japanese LLM - Jnli Exact Match82Score (%)55.3
Open Japanese LLM - Wiki PAS SET F16.37Score (%)50.2
Open Japanese LLM - MR81.8Score (%)49
Open Japanese LLM - RC90.27Score (%)49

Interactive version: theaggregate.ai/model?slug=qwen2-5-7b-o1-ja-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.